f7b64c99b49a7e6e66e6474fa2788fe52b019ed752ae5944187027d1497774a7

README.md

@@ -0,0 +1,24 @@
+---
+base_model: GreenBitAI/Qwen-2.5-7B-Instruct-layer-mix-bpw-4.0
+license: apache-2.0
+tags:
+- mlx
+---
+
+# GreenBitAI/Qwen-2.5-7B-Instruct-layer-mix-bpw-4.0-mlx
+
+This quantized low-bit model [GreenBitAI/Qwen-2.5-7B-Instruct-layer-mix-bpw-4.0-mlx](https://huggingface.co/GreenBitAI/Qwen-2.5-7B-Instruct-layer-mix-bpw-4.0-mlx) was converted to MLX format from [`GreenBitAI/Qwen-2.5-7B-Instruct-layer-mix-bpw-4.0`](https://huggingface.co/GreenBitAI/Qwen-2.5-7B-Instruct-layer-mix-bpw-4.0) using gbx-lm version **0.3.4**.
+Refer to the [original model card](https://huggingface.co/GreenBitAI/Qwen-2.5-7B-Instruct-layer-mix-bpw-4.0) for more details on the model.
+
+## Use with mlx
+
+```bash
+pip install gbx-lm
+```
+
+```python
+from gbx_lm import load, generate
+
+model, tokenizer = load("GreenBitAI/Qwen-2.5-7B-Instruct-layer-mix-bpw-4.0-mlx")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,85 @@
+{
+    "add_cross_attention": false,
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 151643,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 151645,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 3584,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 18944,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 28,
+    "min_length": 0,
+    "model_type": "qwen2",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 28,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "quantization": {
+        "group_size": null,
+        "bits": null
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sep_token_id": null,
+    "sliding_window": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float16",
+    "torchscript": false,
+    "transformers_version": "4.44.0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+}

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e7a3d076aad93b7b5402bc7d7b26a1e8efc05c751d4d3f3c92ae3071e0515b9
+size 1089994878

model.safetensors.index.json

@@ -0,0 +1,1130 @@
+{
+    "metadata": {
+        "total_size": 5651745792
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00002-of-00002.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.channel_scale": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.q_perm": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.zeros": "model-00001-of-00002.safetensors",
+        "model.norm.weight": "model-00001-of-00002.safetensors"
+    }
+}

quant_strategy.json

@@ -0,0 +1,2664 @@
+{
+    "measurement": {
+        "model.layers.0": {
+            "accuracy": 0.8363876342773438,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.1": {
+            "accuracy": 0.9507081508636475,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.2": {
+            "accuracy": 0.9597311019897461,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.3": {
+            "accuracy": 0.983100175857544,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.4": {
+            "accuracy": 0.9927090704441071,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.5": {
+            "accuracy": 0.9934786558151245,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.6": {
+            "accuracy": 0.9899049997329712,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.7": {
+            "accuracy": 0.9921112954616547,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.8": {
+            "accuracy": 0.9914764761924744,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.9": {
+            "accuracy": 0.9910583794116974,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.10": {
+            "accuracy": 0.9924606680870056,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.11": {
+            "accuracy": 0.9926440417766571,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.12": {
+            "accuracy": 0.9924575388431549,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.13": {
+            "accuracy": 0.9924218952655792,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.14": {
+            "accuracy": 0.9918978810310364,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.15": {
+            "accuracy": 0.9919407665729523,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.16": {
+            "accuracy": 0.9919929206371307,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.17": {
+            "accuracy": 0.9913727939128876,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.18": {
+            "accuracy": 0.9900252223014832,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.19": {
+            "accuracy": 0.9880113005638123,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.20": {
+            "accuracy": 0.9862348437309265,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.21": {
+            "accuracy": 0.984893798828125,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.22": {
+            "accuracy": 0.9806430339813232,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.23": {
+            "accuracy": 0.981450617313385,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.24": {
+            "accuracy": 0.9806147217750549,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.25": {
+            "accuracy": 0.9769954681396484,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.26": {
+            "accuracy": 0.9625107049942017,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        },
+        "model.layers.27": {
+            "accuracy": 0.961871862411499,
+            "total_bits": 950390784.0,
+            "o_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "down_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "q_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "k_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "v_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "gate_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            },
+            "up_proj": {
+                "group_size": {
+                    "4": 128
+                },
+                "bits": [
+                    4
+                ],
+                "bits_prop": [
+                    1
+                ],
+                "scale_bits": 4,
+                "scale_groups:": 32
+            }
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}