NEW

added_tokens.json

@@ -1,5 +0,0 @@
-{
-  "<|endoftext|>": 151643,
-  "<|im_end|>": 151645,
-  "<|im_start|>": 151644
-}

config.json

@@ -1,28 +0,0 @@
-{
-  "_name_or_path": "zjunlp/OceanGPT-14B-v0.1",
-  "architectures": [
-    "Qwen2ForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
-  "hidden_act": "silu",
-  "hidden_size": 5120,
-  "initializer_range": 0.02,
-  "intermediate_size": 13696,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 35,
-  "model_type": "qwen2",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 40,
-  "rms_norm_eps": 1e-06,
-  "rope_theta": 1000000.0,
-  "sliding_window": 32768,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.2",
-  "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 152064
-}

generation_config.json

@@ -1,14 +0,0 @@
-{
-  "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "repetition_penalty": 1.05,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
-  "transformers_version": "4.40.2"
-}

model-00001-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:31def49f306b33f0e47e12dbf214a41b8a60e53f18fd1d31a703a37f17469ae0
-size 4919426680

model-00002-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ca26b5a2b3cb9ea0563d3271d8d8d067a12b4ded894b21df094e1ac2d45b7b6b
-size 4991642256

model-00003-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:77b7dbb7bfbf8e3cd74719e085df8e886225c10013bb2eee094801e8a1116677
-size 4991631960

model-00004-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:711209a6bdd7f92de6abdbac72ec3682bd239a6bc021e08effb9634f3a974420
-size 4991631960

model-00005-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:773843ee4a806ea2c5d9f98a4e516efefcb8c67b82473deb1698ee8fa9f8985d
-size 4991631960

model-00006-of-00006.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:29e283702455e40f736182fd7239763ebba87b6867ac0f3e3395393c2e63f28f
-size 3448672536

model.safetensors.index.json

@@ -1,490 +0,0 @@
-{
-  "metadata": {
-    "total_size": 28334581760
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00006-of-00006.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
-    "model.layers.29.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.37.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.38.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
-    "model.norm.weight": "model-00006-of-00006.safetensors"
-  }
-}

special_tokens_map.json

@@ -1,20 +0,0 @@
-{
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
-  "eos_token": {
-    "content": "<|im_end|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
-}

tokenizer_config.json

@@ -1,43 +0,0 @@
-{
-  "add_prefix_space": false,
-  "added_tokens_decoder": {
-    "151643": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151644": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "151645": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [
-    "<|im_start|>",
-    "<|im_end|>"
-  ],
-  "bos_token": null,
-  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
-  "errors": "replace",
-  "model_max_length": 32768,
-  "pad_token": "<|endoftext|>",
-  "split_special_tokens": false,
-  "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
-}