Upload folder using huggingface_hub

README.md

@@ -0,0 +1,59 @@
+---
+license: apache-2.0
+language:
+- fr
+- it
+- de
+- es
+- en
+inference: false
+---
+# Model Card for Mixtral-Fusion-4x7B-Instruct-v0.1
+This model is an experimental model created by merging [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) experts.
+
+# How we merged experts
+We simply take the average of every two experts.weight.  
+The same goes for gate.weight.
+
+# How To Convert
+use colab cpu-high-memory.  
+[convert_mixtral_8x7b_to_4x7b.ipynb](https://huggingface.co/mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1/blob/main/notebook/convert_mixtral_8x7b_to_4x7b.ipynb)
+
+# Usage
+~~~python
+pip install git+https://github.com/huggingface/transformers --upgrade
+pip install torch accelerate bitsandbytes flash_attn
+~~~
+
+~~~python
+from transformers import AutoTokenizer, AutoModelForCausalLM, MixtralForCausalLM
+import torch
+
+model_name_or_path = "mmnga/Mixtral-Fusion-4x7B-Instruct-v0.1"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
+model = MixtralForCausalLM.from_pretrained(model_name_or_path, load_in_8bit=True)
+
+# set num_experts_per_tok 1 or 2 ?
+model.config.num_experts_per_tok = 2
+
+# message
+messages = [
+    {"role": "user", "content": "Tell me what's for dinner tonight."},
+]
+
+with torch.no_grad():
+    token_ids = tokenizer.apply_chat_template(messages, return_tensors="pt")
+    output_ids = model.generate(
+        token_ids.to(model.device),
+        temperature=0.5,
+        do_sample=True,
+        top_p=0.95,
+        top_k=40,
+        max_new_tokens=128,
+        repetition_penalty=1.5
+    )
+output = tokenizer.decode(output_ids[0][token_ids.size(1) :])
+print(output)
+
+~~~

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/tf_models/mixtral-7bx4",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.0.dev0"
+}

model.safetensors.index.json

@@ -0,0 +1,618 @@
+{
+  "metadata": {
+    "total_size": 48307380224
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00010-of-00010.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.block_sparse_moe.gate.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.26.block_sparse_moe.gate.weight": "model-00008-of-00010.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.block_sparse_moe.gate.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00010.safetensors",
+    "model.layers.29.block_sparse_moe.gate.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.block_sparse_moe.gate.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
+    "model.norm.weight": "model-00010-of-00010.safetensors"
+  }
+}

output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df03b153daef993ed87aaa9ba670bc4e8a1c814037f640c6e32b14a5267496fa
+size 8568865776

output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b07bcd804d555ee096b56b1e3d637e28ab6a7975f6f1683176f7a49fc205c82
+size 3757700184

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}