add files

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "pretrain_model/Qwen1.5-14B-Chat",
+  "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": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "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": "4.41.2"
+}

pytorch_model-00001-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f09dfe17c3579d86cbd3f5f4e0aebdf21ec9d8c33416299908a52c3b347fb327
+size 1907132301

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9ef224eba19a39466f2f4f30109a1c115a05228013f9a26f5aa7244994f346
+size 1891535474

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ec4e1a044008ac6389287da90052af561e3fcd902e5a646fdac45f7c98fada
+size 1891535474

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e3f87fa9fa072c667d8ec8f9feeb04270606ea74cba41de5dceae83e664316
+size 1891535474

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b305e81f198bf5041cdfc42d07c2aebc69f0edae736a6a8b7cc05d5ca5dcf081
+size 1891535474

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36298d477084edde43af44ffb4de6a96a6a78c897c060331a1db0c4bc38f936d
+size 1891535474

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d7cb976ce39cb5786f7ea93ddf2dc4155ffa6999340c191a80a9872898fd7b
+size 1891535474

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248b778deaca50826e8dbbdc562753d8ea0e0fde2fee220c9ad3a67b8c8c35e1
+size 1891535474

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e47faf2b572597ac21a9eec4dc5474c21e0b2e7fcca02c891867d5fc658e0e90
+size 1891535474

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727b402c2e0097fa072ffc347b95de5e9136cac70fa1b35fa319fd29205dc96d
+size 1891535474

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a669a35d4a9a22f46615982dd3971a79594a445803a11284cdc23cfdc3af1e
+size 1891535474

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4567c8d525ad23ec3bacb72ded222c8aaf8b6846d395f23fd3336b86b4469edc
+size 1891535474

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e8e049b6fce7c54a02cd876b9f135509612a1c2853a1b37612556a9bdfff8dc
+size 1891535474

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae10a42dc31eb637d79d3469bf60fa9faa685e3d5c58fab3739b17509574a3a
+size 1891535474

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6855d32ec9b0c15f5acb0886f9f51ddb99b450d43f45c36eee0be46dd25bdc
+size 1837663130

pytorch_model.bin.index.json

@@ -0,0 +1,490 @@
+{
+  "metadata": {
+    "total_size": 28334581760
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00015-of-00015.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00005-of-00015.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00005-of-00015.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00005-of-00015.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00006-of-00015.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00006-of-00015.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00006-of-00015.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00007-of-00015.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00007-of-00015.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00007-of-00015.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00007-of-00015.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00008-of-00015.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00008-of-00015.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00008-of-00015.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00008-of-00015.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00008-of-00015.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00008-of-00015.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00008-of-00015.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00008-of-00015.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00008-of-00015.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00009-of-00015.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00009-of-00015.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00009-of-00015.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00009-of-00015.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00009-of-00015.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00009-of-00015.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00009-of-00015.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00010-of-00015.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00010-of-00015.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00010-of-00015.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00010-of-00015.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00010-of-00015.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00010-of-00015.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00010-of-00015.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00011-of-00015.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00011-of-00015.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00011-of-00015.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.self_attn.k_proj.bias": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.self_attn.q_proj.bias": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.self_attn.v_proj.bias": "pytorch_model-00011-of-00015.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.30.self_attn.k_proj.bias": "pytorch_model-00011-of-00015.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.30.self_attn.q_proj.bias": "pytorch_model-00011-of-00015.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.30.self_attn.v_proj.bias": "pytorch_model-00011-of-00015.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.31.self_attn.k_proj.bias": "pytorch_model-00012-of-00015.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.31.self_attn.q_proj.bias": "pytorch_model-00012-of-00015.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.31.self_attn.v_proj.bias": "pytorch_model-00012-of-00015.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.self_attn.k_proj.bias": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.self_attn.q_proj.bias": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.self_attn.v_proj.bias": "pytorch_model-00012-of-00015.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.33.self_attn.k_proj.bias": "pytorch_model-00012-of-00015.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.33.self_attn.q_proj.bias": "pytorch_model-00012-of-00015.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.33.self_attn.v_proj.bias": "pytorch_model-00012-of-00015.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.34.self_attn.k_proj.bias": "pytorch_model-00013-of-00015.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.34.self_attn.q_proj.bias": "pytorch_model-00013-of-00015.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.34.self_attn.v_proj.bias": "pytorch_model-00013-of-00015.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.self_attn.k_proj.bias": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.self_attn.q_proj.bias": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.self_attn.v_proj.bias": "pytorch_model-00013-of-00015.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.36.self_attn.k_proj.bias": "pytorch_model-00013-of-00015.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.36.self_attn.q_proj.bias": "pytorch_model-00013-of-00015.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.36.self_attn.v_proj.bias": "pytorch_model-00013-of-00015.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.37.self_attn.k_proj.bias": "pytorch_model-00014-of-00015.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.37.self_attn.q_proj.bias": "pytorch_model-00014-of-00015.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.37.self_attn.v_proj.bias": "pytorch_model-00014-of-00015.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.self_attn.k_proj.bias": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.self_attn.q_proj.bias": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.self_attn.v_proj.bias": "pytorch_model-00014-of-00015.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
+    "model.layers.39.self_attn.k_proj.bias": "pytorch_model-00014-of-00015.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.39.self_attn.q_proj.bias": "pytorch_model-00014-of-00015.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.39.self_attn.v_proj.bias": "pytorch_model-00014-of-00015.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00004-of-00015.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00004-of-00015.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00004-of-00015.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.norm.weight": "pytorch_model-00015-of-00015.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "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

@@ -0,0 +1,43 @@
+{
+  "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
+}