Upload folder using huggingface_hub

config.json

@@ -0,0 +1,64 @@
+{
+  "_name_or_path": "unsloth/phi-4-unsloth-bnb-4bit",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "eos_token_id": 100265,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "mixtral",
+  "num_attention_heads": 40,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "num_local_experts": 2,
+  "original_max_position_embeddings": 16384,
+  "output_router_logits": false,
+  "pad_token_id": 100351,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection",
+      "model.layers.1.mlp",
+      "model.layers.2.mlp",
+      "model.layers.3.mlp",
+      "model.layers.37.self_attn.o_proj",
+      "model.layers.39.self_attn.o_proj"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 100352
+}

mergekit_moe_config.yml

@@ -0,0 +1,7 @@
+base_model: unsloth/phi-4-unsloth-bnb-4bit
+gate_mode: random
+architecture: mixtral
+dtype: bfloat16
+experts:
+  - source_model: unsloth/phi-4-unsloth-bnb-4bit
+  - source_model: unsloth/phi-4-unsloth-bnb-4bit

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffce9bc12200cdaa7866871f9ff628f2df31b7cf4c8d691be96357bf93ef9536
+size 4959852360

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf423ff1b8ddf43893e78e1417c92c271b106c951b25f534b2fd0f50624c979
+size 4928482824

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc1aa8da9e40af51ad2f16202a6f85c6ee309bdd591cbc2e2da472fa0f95283
+size 4928483032

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7aafa0492720843e015362b1ccec85df372998bd79767a10d9b7fb84c685af
+size 4928483032

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78376586200e1a5c5626d9247965fa6c7dfaaef5d3301149ab79fe3fb451d5aa
+size 4928483032

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ec5cdc373f634950bb6774fcbbea3efefd08ed5996f289b41c48f842823651
+size 3728610312

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 28402329600}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00006.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00006.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00006.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00006.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00006.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00006.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00006.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00006.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.32.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.32.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.32.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.32.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.32.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.32.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.33.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.33.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.33.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.33.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.33.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.33.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.34.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.34.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.34.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.34.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.34.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00006.safetensors", "model.layers.34.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00006.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors", "model.layers.35.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00006.safetensors", "model.layers.35.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00006.safetensors", "model.layers.35.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00006.safetensors", "model.layers.35.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00006.safetensors", "model.layers.35.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.35.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.36.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.36.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.36.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.36.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.36.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.36.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.37.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.37.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.37.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.37.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.37.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.37.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.38.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.38.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.38.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.38.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.38.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.38.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors", "model.layers.39.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00006.safetensors", "model.layers.39.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00006.safetensors", "model.layers.39.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00006.safetensors", "model.layers.39.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00006.safetensors", "model.layers.39.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00006.safetensors", "model.layers.39.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00006.safetensors", "model.norm.weight": "model-00006-of-00006.safetensors", "lm_head.weight": "model-00006-of-00006.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.32.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.33.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.34.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.35.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.36.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.37.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.38.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors", "model.layers.39.block_sparse_moe.gate.weight": "model-00006-of-00006.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "�",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,791 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "5809": {
+      "content": "�",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100256": {
+      "content": "<|dummy_0|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|dummy_1|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|dummy_2|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|dummy_3|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|im_sep|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|dummy_4|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|dummy_5|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|dummy_6|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|dummy_7|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|dummy_8|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|dummy_9|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|dummy_10|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|dummy_11|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|dummy_12|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|dummy_13|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "<|dummy_14|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "<|dummy_15|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100280": {
+      "content": "<|dummy_16|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100281": {
+      "content": "<|dummy_17|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100282": {
+      "content": "<|dummy_18|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100283": {
+      "content": "<|dummy_19|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100284": {
+      "content": "<|dummy_20|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100285": {
+      "content": "<|dummy_21|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100286": {
+      "content": "<|dummy_22|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100287": {
+      "content": "<|dummy_23|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100288": {
+      "content": "<|dummy_24|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100289": {
+      "content": "<|dummy_25|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100290": {
+      "content": "<|dummy_26|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100291": {
+      "content": "<|dummy_27|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100292": {
+      "content": "<|dummy_28|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100293": {
+      "content": "<|dummy_29|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100294": {
+      "content": "<|dummy_30|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100295": {
+      "content": "<|dummy_31|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100296": {
+      "content": "<|dummy_32|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100297": {
+      "content": "<|dummy_33|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100298": {
+      "content": "<|dummy_34|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100299": {
+      "content": "<|dummy_35|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100300": {
+      "content": "<|dummy_36|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100301": {
+      "content": "<|dummy_37|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100302": {
+      "content": "<|dummy_38|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100303": {
+      "content": "<|dummy_39|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100304": {
+      "content": "<|dummy_40|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100305": {
+      "content": "<|dummy_41|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100306": {
+      "content": "<|dummy_42|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100307": {
+      "content": "<|dummy_43|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100308": {
+      "content": "<|dummy_44|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100309": {
+      "content": "<|dummy_45|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100310": {
+      "content": "<|dummy_46|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100311": {
+      "content": "<|dummy_47|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100312": {
+      "content": "<|dummy_48|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100313": {
+      "content": "<|dummy_49|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100314": {
+      "content": "<|dummy_50|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100315": {
+      "content": "<|dummy_51|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100316": {
+      "content": "<|dummy_52|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100317": {
+      "content": "<|dummy_53|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100318": {
+      "content": "<|dummy_54|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100319": {
+      "content": "<|dummy_55|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100320": {
+      "content": "<|dummy_56|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100321": {
+      "content": "<|dummy_57|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100322": {
+      "content": "<|dummy_58|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100323": {
+      "content": "<|dummy_59|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100324": {
+      "content": "<|dummy_60|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100325": {
+      "content": "<|dummy_61|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100326": {
+      "content": "<|dummy_62|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100327": {
+      "content": "<|dummy_63|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100328": {
+      "content": "<|dummy_64|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100329": {
+      "content": "<|dummy_65|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100330": {
+      "content": "<|dummy_66|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100331": {
+      "content": "<|dummy_67|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100332": {
+      "content": "<|dummy_68|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100333": {
+      "content": "<|dummy_69|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100334": {
+      "content": "<|dummy_70|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100335": {
+      "content": "<|dummy_71|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100336": {
+      "content": "<|dummy_72|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100337": {
+      "content": "<|dummy_73|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100338": {
+      "content": "<|dummy_74|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100339": {
+      "content": "<|dummy_75|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100340": {
+      "content": "<|dummy_76|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100341": {
+      "content": "<|dummy_77|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100342": {
+      "content": "<|dummy_78|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100343": {
+      "content": "<|dummy_79|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100344": {
+      "content": "<|dummy_80|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100345": {
+      "content": "<|dummy_81|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100346": {
+      "content": "<|dummy_82|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100347": {
+      "content": "<|dummy_83|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100348": {
+      "content": "<|dummy_84|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100349": {
+      "content": "<|dummy_85|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100350": {
+      "content": "<|dummy_86|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100351": {
+      "content": "<|dummy_87|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "�"
+}