Upload folder using huggingface_hub

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

pytorch_model-00001-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77256686419db33f566435c301d7a1d70cd364cdbdda947412aff3784c07796a
+size 1923210568

pytorch_model-00002-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84f5758a87e0da9c263d92d9f5eadfb0b172592c859301804fd6a61156578e21
+size 1864478730

pytorch_model-00003-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdfd31b094a16622fce5366dd1aed4d9d977635955247eead77785da80ccf6cb
+size 1864478794

pytorch_model-00004-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c90b7045f8f9beaacee7a5d2b79cb4eaa2c7a049aab8b234074deed6ae05918
+size 1864478794

pytorch_model-00005-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5285029ee5ae4ec286049e6db4dfa9e6dcd3919a22d84b979519d910bfec09ca
+size 1864478794

pytorch_model-00006-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3acb6cd99fdb5c913c51065465a789c2067f69171d8a6cec4624478eedf67fe
+size 1864478794

pytorch_model-00007-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79eb54825fa6c025c10e09eed9bf2fb67bc76191749d2f1832996d7499a4825
+size 1864478794

pytorch_model-00008-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c62a662721bdd6a48b25ad693ed5e9369b11654f7418cb2ea3843c188df44c7
+size 1805746956

pytorch_model-00009-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37a131e4f36c3fe3c28d6ad8fe4ad7844b0d4b216bea7743f6ad93a8b4ac3fc
+size 1090003606

pytorch_model-00010-of-00010.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baf3731c37837a8dea1b2e7cd93a008f9c1974b5978214c1692a732a8a7e588e
+size 1089996165

pytorch_model.bin.index.json

@@ -0,0 +1,394 @@
+{
+  "metadata": {
+    "total_size": 17095695360
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00010-of-00010.bin",
+    "model.embed_tokens.weight": "pytorch_model-00009-of-00010.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00004-of-00010.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00010.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00005-of-00010.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00010.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00006-of-00010.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00010.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00007-of-00010.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00010.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.29.self_attn.k_proj.bias": "pytorch_model-00008-of-00010.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.29.self_attn.q_proj.bias": "pytorch_model-00008-of-00010.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.29.self_attn.v_proj.bias": "pytorch_model-00008-of-00010.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.30.self_attn.k_proj.bias": "pytorch_model-00008-of-00010.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.30.self_attn.q_proj.bias": "pytorch_model-00008-of-00010.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.30.self_attn.v_proj.bias": "pytorch_model-00008-of-00010.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.self_attn.k_proj.bias": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.self_attn.q_proj.bias": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.self_attn.v_proj.bias": "pytorch_model-00008-of-00010.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00010.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00001-of-00010.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00010.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00002-of-00010.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00010.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00003-of-00010.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00010.bin",
+    "model.norm.weight": "pytorch_model-00009-of-00010.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": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}