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": "Z:\\Project\\FlowLoom\\model_pretrain\\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": 28,
+  "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
+}

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"
+}

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b97765df8524a3a7488b14a8dd17c1224067c650632e48ea04ae14c56c0833c3
+size 1089994896

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e032632c783be13fdf94609d0fa3548125c44281dbbdaad96c3083601bcfa6
+size 990964136

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a684c2f6458c80b7b9f8a77b4da9410f19aac5e4b44085478451b8786c13fc6
+size 932233880

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26bfffb9196f14bf1da9c0cd06ed98d3667bf0b8701fec40b7efdccf7e31d216
+size 932233880

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc5c58bb5130fb4270d72a680a18f77e40e3d4a9a125eefbd594fa4f2d8f8c3b
+size 932233880

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31f35e0976e2bfcfa156831491df3d9d808863de8245747aa48fbeaf21f4b48
+size 932233872

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db71bcf5afc97aad3c4500b6102dd093b8e689b70bcb16e088c04387dd885f66
+size 932233904

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a0484d27e5ad2a5f4e0632f80571c9cd4c2367d9ee3a9f1df14ab761ea41fb1
+size 932233904

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5ee81f8bac2e62bb698deadad539c3bfdac6f054ad37355037cedf34f79c461
+size 932233904

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a8d9f9ced45f12f3de7c829f679c30abe7bacbeb0f79c44ac78246afaef106
+size 932233904

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e042f80cca15b7977f260d5f273e6ca8bd6ce3ae4e29501d30c71631bf52e06
+size 932233904

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82de2393a37ab0cf2172f2a265e4d149a400087117a1075a0fe3f00788380f64
+size 932233904

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a74e0815ab9e5d5da564f7bcf61ff47afe2a637cb98ac5cb79eba78dc7a3161
+size 932233904

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6ac8ea8785fc4ed4ef58650dd219e66b4ce101f6d2758900e70f8e5bc1ae87d
+size 932233904

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8579a3bca95803bad31c0edcf8fdcdd160918fd10f62203de943730b050af3f4
+size 873510904

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac6627211ff04f97774bfc266adba6c06570b92bde4daeaef386bee978187412
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00016-of-00016.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00016.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00015-of-00016.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00015-of-00016.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
+    "model.norm.weight": "model-00015-of-00016.safetensors"
+  }
+}

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": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}