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/Qwen1.5-7B-Chat",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "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": 151936
+}

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": "4.40.2"
+}

pytorch_model-00001-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a95a65fca8e36e3793b60d15244846dacb62374c497aeaa2d22e3689c04ba33
+size 1244661125

pytorch_model-00002-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64fded22ffa19b53aba72a18edf7750efa4921da426f92bc0cb8d019ecbe65ee
+size 943835608

pytorch_model-00003-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f156a642948862cb44ec8fcd9ea3fa7ab47e9eb9c016570b9237f22d10ac6e20
+size 989946814

pytorch_model-00004-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:370b93f576a04a780d6a5719fa64062c690235d03e0a1c2587031f4038f1dcc3
+size 966912472

pytorch_model-00005-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72b7f7bc0715ec4548a160f2e3d68e300d0348a55a6fc6ef86a53f524801e40
+size 966887010

pytorch_model-00006-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dafac695c56c356d9696ae633a357543f89a130c892d70ac151a34f35c4dc45
+size 989963874

pytorch_model-00007-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:542e020463a4a2e24dfa8ef2cdc5eea1502bd1a4ef573f4a8907acd7e90adb8d
+size 943835672

pytorch_model-00008-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba94915fbe6b5631d3bc3c531365d11a6ec918efb4f7d7a8d09f1ce37555c171
+size 989946878

pytorch_model-00009-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16f7155aa7199a2281e8aeeda47c9828ae83b65275ac68ff39c8c7dc48f8064
+size 966912536

pytorch_model-00010-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:debe2d2a5b44a22b36ebfd44fdc38ee54dd2027a199dfe6143f06eba05b86d4e
+size 966887010

pytorch_model-00011-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49190bd49537ba5ca5b4452831eb8256064fe0b106e668789795abc2535cfe4c
+size 989963874

pytorch_model-00012-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c86bee06b1aa5fd78e0d9c03b5434272bd7659bb94e0a55c967456a0d9bffd95
+size 943835672

pytorch_model-00013-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a907a670988d734afef23e0b59f3f406219134959d95810e671e57fd584cd2be
+size 989946878

pytorch_model-00014-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29fe05a5f6400737bb76cde6f628c44ae936a10de55ec97cf805f34b9869dfb4
+size 966912536

pytorch_model-00015-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb7463d4faa6d85fb675396248e7b61ca68b5e375ea04340873d2a8596696c1b
+size 337678093

pytorch_model-00016-of-00016.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c812f14f11f95b5b18c6ce7a7fa5ebcf17e63bb7b0cc6963502d36fe3b8b9c
+size 1244661125

pytorch_model.bin.index.json

@@ -0,0 +1,394 @@
+{
+  "metadata": {
+    "total_size": 15442649088
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00016-of-00016.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00016.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.0.self_attn.k_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.0.self_attn.q_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.0.self_attn.v_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.self_attn.k_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.self_attn.q_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.self_attn.v_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.10.self_attn.k_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.10.self_attn.q_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.10.self_attn.v_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.self_attn.k_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.self_attn.q_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.self_attn.v_proj.bias": "pytorch_model-00006-of-00016.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.12.self_attn.k_proj.bias": "pytorch_model-00007-of-00016.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.12.self_attn.q_proj.bias": "pytorch_model-00007-of-00016.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.12.self_attn.v_proj.bias": "pytorch_model-00007-of-00016.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.self_attn.k_proj.bias": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.self_attn.q_proj.bias": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.self_attn.v_proj.bias": "pytorch_model-00007-of-00016.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.14.self_attn.k_proj.bias": "pytorch_model-00007-of-00016.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.14.self_attn.q_proj.bias": "pytorch_model-00007-of-00016.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.14.self_attn.v_proj.bias": "pytorch_model-00007-of-00016.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00016.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.15.self_attn.k_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.15.self_attn.q_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.15.self_attn.v_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.16.self_attn.k_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.16.self_attn.q_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.16.self_attn.v_proj.bias": "pytorch_model-00008-of-00016.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00016.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.17.self_attn.k_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.17.self_attn.q_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.17.self_attn.v_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.self_attn.k_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.self_attn.q_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.self_attn.v_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.19.self_attn.k_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.19.self_attn.q_proj.bias": "pytorch_model-00009-of-00016.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00016.bin",
+    "model.layers.19.self_attn.v_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.2.self_attn.k_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.2.self_attn.q_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.2.self_attn.v_proj.bias": "pytorch_model-00002-of-00016.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00016.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.20.self_attn.k_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.20.self_attn.q_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.20.self_attn.v_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.21.self_attn.k_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.21.self_attn.q_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.21.self_attn.v_proj.bias": "pytorch_model-00010-of-00016.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00016.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.22.self_attn.k_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.22.self_attn.q_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.22.self_attn.v_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.self_attn.k_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.self_attn.q_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.self_attn.v_proj.bias": "pytorch_model-00011-of-00016.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00011-of-00016.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.24.self_attn.k_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.24.self_attn.q_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.24.self_attn.v_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.self_attn.k_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.self_attn.q_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.self_attn.v_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.26.self_attn.k_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.26.self_attn.q_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.26.self_attn.v_proj.bias": "pytorch_model-00012-of-00016.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00016.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.27.self_attn.k_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.27.self_attn.q_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.27.self_attn.v_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.28.self_attn.k_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.28.self_attn.q_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.28.self_attn.v_proj.bias": "pytorch_model-00013-of-00016.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00016.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.29.self_attn.k_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.29.self_attn.q_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.29.self_attn.v_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.3.self_attn.k_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.3.self_attn.q_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.3.self_attn.v_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.30.self_attn.k_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.30.self_attn.q_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.30.self_attn.v_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.31.self_attn.k_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.31.self_attn.q_proj.bias": "pytorch_model-00014-of-00016.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014-of-00016.bin",
+    "model.layers.31.self_attn.v_proj.bias": "pytorch_model-00015-of-00016.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00015-of-00016.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.4.self_attn.k_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.4.self_attn.q_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.4.self_attn.v_proj.bias": "pytorch_model-00003-of-00016.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00016.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.5.self_attn.k_proj.bias": "pytorch_model-00004-of-00016.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.5.self_attn.q_proj.bias": "pytorch_model-00004-of-00016.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.5.self_attn.v_proj.bias": "pytorch_model-00004-of-00016.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.self_attn.k_proj.bias": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.self_attn.q_proj.bias": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.self_attn.v_proj.bias": "pytorch_model-00004-of-00016.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.7.self_attn.k_proj.bias": "pytorch_model-00004-of-00016.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.7.self_attn.q_proj.bias": "pytorch_model-00004-of-00016.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00016.bin",
+    "model.layers.7.self_attn.v_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.self_attn.k_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.self_attn.q_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.self_attn.v_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00006-of-00016.bin",
+    "model.layers.9.self_attn.k_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.9.self_attn.q_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.layers.9.self_attn.v_proj.bias": "pytorch_model-00005-of-00016.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00016.bin",
+    "model.norm.weight": "pytorch_model-00015-of-00016.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 +1,44 @@
+{
+  "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": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}