Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 25600,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 64,
+  "model_type": "qwen3",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.1"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f715abdb51f6b9e957b32c940a95b3b50bc833816c019f3611cf93fd9da990ef
+size 4760708512

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9885ac46aec03ff1c69672d55263b7a91ec85c97ebb22c45fa60b060f86a47b
+size 3523365248

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb4690ab2a43fa29714503fb4486856856248fbe61ee4eb7a7cc92e27209615c
+size 4953257920

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b646c939efea566cdd8cb6afa816ef36a1f280e93a0d294c76c16760365916ef
+size 4855027600

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d19e89fad330b0229871b744bebc10bb815065fe0d5b45f5ef2a5efafc408def
+size 4928417928

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c27688521752f5f31a6a6ac13de4c7281d1664c5988db934af115633527ace4
+size 4959971280

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386275ccd3ac7b1dc01f31999de660c1c917aa6dc75d1fc08bee8e6fdba40657
+size 4980806992

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd8660479579ca496f9d03a8fb1b611dcde75c9673efc435cd90012f5712eaed
+size 4938895280

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23332c899c67ff66958f57d077c9b742f6bd44463e2fcffbd9fc30219de0d49a
+size 4980806280

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:378bdff6de6e8e4c599f1a8e5faa314f79bec08f4fb8af77410385827c5de3f7
+size 3974159968

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ca609a35000024ab8f219efdc1a8f9b836544226f514fd85c0e4759c46f041
+size 4921831320

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef23c1352d30951ef19db96290027ec3b655aeb2a9275823f920877ee6cbb2cd
+size 4970351848

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1a2d5d3dd80cbc8eb1321e8cba716c0a1995be225c9a7b168f00530d23f8277
+size 4980815496

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed41c7ee7fb5188f6289fcae8e2067de8332968d4efbc18b2ff847b0e33a5b0
+size 3795912784

model.safetensors.index.json

@@ -0,0 +1,714 @@
+{
+  "metadata": {
+    "total_size": 65524246528
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00011-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00003-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.40.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.40.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.41.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.41.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.42.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.42.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.43.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.43.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.44.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.44.self_attn.q_norm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.45.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.45.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.46.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.46.self_attn.q_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.47.self_attn.k_norm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.47.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.48.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.48.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.49.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.49.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.50.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.50.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.51.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.51.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.52.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.52.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.53.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.53.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.54.self_attn.k_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.54.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.55.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.55.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.56.self_attn.k_norm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.56.self_attn.q_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.57.self_attn.k_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.57.self_attn.q_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.58.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.58.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.59.self_attn.k_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.59.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.60.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.60.self_attn.q_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.61.self_attn.k_norm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.61.self_attn.q_norm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.62.self_attn.k_norm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.62.self_attn.q_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.63.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.63.self_attn.q_norm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.norm.weight": "model-00011-of-00014.safetensors"
+  }
+}

outputs/2025-08-05/12-01-37/.hydra/config.yaml

@@ -0,0 +1,366 @@
+actor_rollout_ref:
+  actor:
+    strategy: fsdp
+    ppo_mini_batch_size: 32
+    ppo_micro_batch_size: null
+    ppo_micro_batch_size_per_gpu: 2
+    use_dynamic_bsz: false
+    ppo_max_token_len_per_gpu: 16384
+    clip_ratio: 0.2
+    clip_ratio_low: 0.2
+    clip_ratio_high: 0.2
+    policy_loss:
+      loss_mode: vanilla
+      clip_cov_ratio: 0.0002
+      clip_cov_lb: 1.0
+      clip_cov_ub: 5.0
+      kl_cov_ratio: 0.0002
+      ppo_kl_coef: 0.1
+    clip_ratio_c: 3.0
+    loss_agg_mode: token-mean
+    entropy_coeff: 0
+    use_kl_loss: true
+    use_torch_compile: true
+    kl_loss_coef: 0.001
+    kl_loss_type: low_var_kl
+    ppo_epochs: 1
+    shuffle: false
+    checkpoint:
+      save_contents:
+      - model
+      - optimizer
+      - extra
+      load_contents: ${.save_contents}
+    optim:
+      lr: 5.0e-07
+      lr_warmup_steps_ratio: 0.0
+      total_training_steps: -1
+      weight_decay: 0.01
+      lr_warmup_steps: -1
+      min_lr_ratio: 0.0
+      num_cycles: 0.5
+      warmup_style: constant
+    grad_clip: 1.0
+    ulysses_sequence_parallel_size: 1
+    entropy_from_logits_with_chunking: false
+    entropy_checkpointing: false
+    fsdp_config:
+      wrap_policy:
+        min_num_params: 0
+      param_offload: false
+      optimizer_offload: false
+      offload_policy: false
+      reshard_after_forward: true
+      fsdp_size: -1
+      forward_prefetch: false
+      model_dtype: bf16
+  ref:
+    strategy: ${actor_rollout_ref.actor.strategy}
+    use_torch_compile: ${oc.select:actor_rollout_ref.actor.use_torch_compile,true}
+    log_prob_micro_batch_size: null
+    log_prob_micro_batch_size_per_gpu: 2
+    log_prob_use_dynamic_bsz: ${oc.select:actor_rollout_ref.actor.use_dynamic_bsz,false}
+    log_prob_max_token_len_per_gpu: ${oc.select:actor_rollout_ref.actor.ppo_max_token_len_per_gpu,16384}
+    fsdp_config:
+      param_offload: false
+      reshard_after_forward: true
+      forward_prefetch: false
+      wrap_policy:
+        min_num_params: 0
+      model_dtype: bf16
+    ulysses_sequence_parallel_size: ${oc.select:actor_rollout_ref.actor.ulysses_sequence_parallel_size,1}
+    entropy_from_logits_with_chunking: false
+    entropy_checkpointing: false
+  rollout:
+    name: vllm
+    mode: sync
+    temperature: 1.0
+    top_k: -1
+    top_p: 1
+    prompt_length: ${oc.select:data.max_prompt_length,512}
+    response_length: ${oc.select:data.max_response_length,512}
+    dtype: bfloat16
+    gpu_memory_utilization: 0.7
+    ignore_eos: false
+    enforce_eager: true
+    free_cache_engine: true
+    tensor_model_parallel_size: 4
+    max_num_batched_tokens: 8192
+    max_model_len: null
+    max_num_seqs: 1024
+    log_prob_micro_batch_size: null
+    log_prob_micro_batch_size_per_gpu: 4
+    log_prob_use_dynamic_bsz: ${oc.select:actor_rollout_ref.actor.use_dynamic_bsz,false}
+    log_prob_max_token_len_per_gpu: ${oc.select:actor_rollout_ref.actor.ppo_max_token_len_per_gpu,16384}
+    disable_log_stats: true
+    do_sample: true
+    'n': 4
+    multi_stage_wake_up: false
+    engine_kwargs:
+      vllm:
+        swap_space: null
+        disable_mm_preprocessor_cache: false
+      sglang:
+        attention_backend: null
+    val_kwargs:
+      top_k: -1
+      top_p: 1.0
+      temperature: 0
+      'n': 1
+      do_sample: false
+    multi_turn:
+      enable: false
+      max_assistant_turns: null
+      tool_config_path: null
+      max_user_turns: null
+      max_parallel_calls: 1
+      max_tool_response_length: 256
+      tool_response_truncate_side: middle
+      interaction_config_path: null
+      completion_callback: null
+      use_inference_chat_template: false
+      tokenization_sanity_check_mode: strict
+      format: hermes
+    calculate_log_probs: false
+    agent:
+      num_workers: 8
+      agent_loop_config_path: null
+      custom_async_server:
+        path: null
+        name: null
+    update_weights_bucket_megabytes: 512
+    trace:
+      backend: null
+      token2text: false
+    enable_chunked_prefill: true
+    load_format: dummy_dtensor
+    layered_summon: false
+  hybrid_engine: true
+  model:
+    path: //home/Competition2025/P12/P12U007/training/sft_Qwen3_math/checkpoints/global_step_116/huggingface
+    custom_chat_template: null
+    use_shm: false
+    external_lib: null
+    override_config: {}
+    enable_gradient_checkpointing: true
+    enable_activation_offload: false
+    use_remove_padding: true
+    lora_rank: 0
+    lora_alpha: 16
+    target_modules: all-linear
+    exclude_modules: null
+    use_liger: false
+    use_fused_kernels: false
+    fused_kernel_options:
+      impl_backend: torch
+    trust_remote_code: false
+    attn_implementation: flash_attention_2
+  profiler:
+    _target_: verl.utils.profiler.ProfilerConfig
+    discrete: false
+    all_ranks: false
+    ranks: []
+trainer:
+  npu_profile:
+    options:
+      save_path: ./profiler_data
+      level: level1
+      with_memory: false
+      record_shapes: false
+      with_npu: true
+      with_cpu: true
+      with_module: false
+      with_stack: false
+      analysis: true
+  balance_batch: true
+  total_epochs: 15
+  total_training_steps: null
+  profile_steps: null
+  controller_nsight_options:
+    trace: cuda,nvtx,cublas,ucx
+    cuda-memory-usage: 'true'
+    cuda-graph-trace: graph
+  worker_nsight_options:
+    trace: cuda,nvtx,cublas,ucx
+    cuda-memory-usage: 'true'
+    cuda-graph-trace: graph
+    capture-range: cudaProfilerApi
+    capture-range-end: null
+    kill: none
+  project_name: Qwen3_32B_SFT+GRPO
+  experiment_name: Qwen3_32B_SFT_MATH
+  logger:
+  - console
+  - wandb
+  log_val_generations: 0
+  rollout_data_dir: null
+  validation_data_dir: null
+  nnodes: 1
+  n_gpus_per_node: 8
+  save_freq: 50
+  esi_redundant_time: 0
+  resume_mode: auto
+  resume_from_path: null
+  val_before_train: true
+  val_only: false
+  test_freq: 50
+  critic_warmup: 0
+  default_hdfs_dir: null
+  del_local_ckpt_after_load: false
+  default_local_dir: /home/Competition2025/P12/P12U007/training/grpo_001/checkpoints
+  max_actor_ckpt_to_keep: null
+  max_critic_ckpt_to_keep: null
+  ray_wait_register_center_timeout: 300
+  device: cuda
+  use_legacy_worker_impl: auto
+data:
+  tokenizer: null
+  use_shm: false
+  train_files: /home/Competition2025/P12/P12U007/data/gsm8k/train.parquet
+  val_files: /home/Competition2025/P12/P12U007/data/gsm8k/test.parquet
+  prompt_key: prompt
+  reward_fn_key: data_source
+  max_prompt_length: 512
+  max_response_length: 1024
+  train_batch_size: 64
+  val_batch_size: null
+  return_raw_input_ids: false
+  return_raw_chat: false
+  return_full_prompt: false
+  shuffle: true
+  dataloader_num_workers: 0
+  validation_shuffle: false
+  filter_overlong_prompts: false
+  filter_overlong_prompts_workers: 1
+  truncation: error
+  image_key: images
+  video_key: videos
+  trust_remote_code: false
+  custom_cls:
+    path: null
+    name: null
+  return_multi_modal_inputs: true
+  sampler:
+    class_path: null
+    class_name: null
+  datagen:
+    path: null
+    name: null
+critic:
+  rollout_n: ${oc.select:actor_rollout_ref.rollout.n,1}
+  strategy: fsdp
+  optim:
+    lr_warmup_steps_ratio: 0.0
+    total_training_steps: -1
+    weight_decay: 0.01
+    lr: 1.0e-05
+    min_lr_ratio: null
+    warmup_style: constant
+  model:
+    path: ~/models/deepseek-llm-7b-chat
+    tokenizer_path: ${oc.select:actor_rollout_ref.model.path,"~/models/deepseek-llm-7b-chat"}
+    override_config: {}
+    external_lib: ${oc.select:actor_rollout_ref.model.external_lib,null}
+    trust_remote_code: ${oc.select:actor_rollout_ref.model.trust_remote_code,false}
+    use_shm: false
+    enable_gradient_checkpointing: true
+    enable_activation_offload: false
+    use_remove_padding: false
+    fsdp_config:
+      param_offload: false
+      optimizer_offload: false
+      offload_policy: false
+      reshard_after_forward: true
+      wrap_policy:
+        min_num_params: 0
+      fsdp_size: -1
+      forward_prefetch: false
+    lora_rank: 0
+    lora_alpha: 16
+    target_modules: all-linear
+  ppo_mini_batch_size: ${oc.select:actor_rollout_ref.actor.ppo_mini_batch_size,256}
+  ppo_micro_batch_size: null
+  ppo_micro_batch_size_per_gpu: ${oc.select:.ppo_micro_batch_size,null}
+  use_dynamic_bsz: ${oc.select:actor_rollout_ref.actor.use_dynamic_bsz,false}
+  ppo_max_token_len_per_gpu: 32768
+  forward_max_token_len_per_gpu: ${.ppo_max_token_len_per_gpu}
+  ppo_epochs: ${oc.select:actor_rollout_ref.actor.ppo_epochs,1}
+  shuffle: ${oc.select:actor_rollout_ref.actor.shuffle,false}
+  cliprange_value: 0.5
+  loss_agg_mode: ${oc.select:actor_rollout_ref.actor.loss_agg_mode,token-mean}
+  checkpoint:
+    save_contents:
+    - model
+    - optimizer
+    - extra
+    load_contents: ${.save_contents}
+  profiler:
+    _target_: verl.utils.profiler.ProfilerConfig
+    discrete: false
+    all_ranks: false
+    ranks: []
+  _target_: verl.trainer.config.FSDPCriticConfig
+  forward_micro_batch_size: ${oc.select:.ppo_micro_batch_size,null}
+  forward_micro_batch_size_per_gpu: ${oc.select:.ppo_micro_batch_size_per_gpu,null}
+  ulysses_sequence_parallel_size: 1
+  grad_clip: 1.0
+reward_model:
+  enable: false
+  strategy: fsdp
+  model:
+    input_tokenizer: ${actor_rollout_ref.model.path}
+    path: ~/models/FsfairX-LLaMA3-RM-v0.1
+    external_lib: ${actor_rollout_ref.model.external_lib}
+    trust_remote_code: false
+    use_shm: false
+    use_remove_padding: false
+    use_fused_kernels: ${actor_rollout_ref.model.use_fused_kernels}
+    fsdp_config:
+      wrap_policy:
+        min_num_params: 0
+      param_offload: false
+      reshard_after_forward: true
+      fsdp_size: -1
+      forward_prefetch: false
+  micro_batch_size: null
+  micro_batch_size_per_gpu: null
+  max_length: null
+  use_dynamic_bsz: ${critic.use_dynamic_bsz}
+  forward_max_token_len_per_gpu: ${critic.forward_max_token_len_per_gpu}
+  reward_manager: naive
+  launch_reward_fn_async: false
+  sandbox_fusion:
+    url: null
+    max_concurrent: 64
+    memory_limit_mb: 1024
+  profiler:
+    _target_: verl.utils.profiler.ProfilerConfig
+    discrete: false
+    all_ranks: false
+    ranks: []
+  ulysses_sequence_parallel_size: 1
+custom_reward_function:
+  path: null
+  name: compute_score
+algorithm:
+  _target_: verl.trainer.config.AlgoConfig
+  gamma: 1.0
+  lam: 1.0
+  adv_estimator: grpo
+  norm_adv_by_std_in_grpo: true
+  use_kl_in_reward: false
+  kl_penalty: kl
+  kl_ctrl:
+    _target_: verl.trainer.config.KLControlConfig
+    type: fixed
+    kl_coef: 0.001
+    horizon: 10000
+    target_kl: 0.1
+  use_pf_ppo: false
+  pf_ppo:
+    _target_: verl.trainer.config.PFPPOConfig
+    reweight_method: pow
+    weight_pow: 2.0
+ray_init:
+  num_cpus: null
+  timeline_json_file: null

outputs/2025-08-05/12-01-37/.hydra/hydra.yaml

@@ -0,0 +1,192 @@
+hydra:
+  run:
+    dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S}
+  sweep:
+    dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task:
+    - data.train_files=/home/Competition2025/P12/P12U007/data/gsm8k/train.parquet
+    - data.val_files=/home/Competition2025/P12/P12U007/data/gsm8k/test.parquet
+    - data.train_batch_size=64
+    - data.max_prompt_length=512
+    - data.max_response_length=1024
+    - data.dataloader_num_workers=0
+    - actor_rollout_ref.model.path=//home/Competition2025/P12/P12U007/training/sft_Qwen3_math/checkpoints/global_step_116/huggingface
+    - actor_rollout_ref.model.use_remove_padding=True
+    - actor_rollout_ref.actor.optim.lr=5e-7
+    - actor_rollout_ref.actor.ppo_mini_batch_size=32
+    - actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=2
+    - actor_rollout_ref.actor.use_kl_loss=True
+    - actor_rollout_ref.actor.kl_loss_coef=0.001
+    - +actor_rollout_ref.actor.fsdp_config.model_dtype=bf16
+    - +actor_rollout_ref.ref.fsdp_config.model_dtype=bf16
+    - +actor_rollout_ref.model.attn_implementation=flash_attention_2
+    - actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=4
+    - actor_rollout_ref.rollout.tensor_model_parallel_size=4
+    - actor_rollout_ref.rollout.gpu_memory_utilization=0.7
+    - actor_rollout_ref.rollout.n=4
+    - actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=2
+    - algorithm.adv_estimator=grpo
+    - trainer.n_gpus_per_node=8
+    - trainer.nnodes=1
+    - trainer.save_freq=50
+    - trainer.test_freq=50
+    - trainer.default_local_dir=/home/Competition2025/P12/P12U007/training/grpo_001/checkpoints
+    - trainer.logger=[console,wandb]
+    - trainer.project_name=Qwen3_32B_SFT+GRPO
+    - trainer.experiment_name=Qwen3_32B_SFT_MATH
+    - trainer.total_epochs=15
+  job:
+    name: main_ppo
+    chdir: null
+    override_dirname: +actor_rollout_ref.actor.fsdp_config.model_dtype=bf16,+actor_rollout_ref.model.attn_implementation=flash_attention_2,+actor_rollout_ref.ref.fsdp_config.model_dtype=bf16,actor_rollout_ref.actor.kl_loss_coef=0.001,actor_rollout_ref.actor.optim.lr=5e-7,actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=2,actor_rollout_ref.actor.ppo_mini_batch_size=32,actor_rollout_ref.actor.use_kl_loss=True,actor_rollout_ref.model.path=//home/Competition2025/P12/P12U007/training/sft_Qwen3_math/checkpoints/global_step_116/huggingface,actor_rollout_ref.model.use_remove_padding=True,actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=2,actor_rollout_ref.rollout.gpu_memory_utilization=0.7,actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=4,actor_rollout_ref.rollout.n=4,actor_rollout_ref.rollout.tensor_model_parallel_size=4,algorithm.adv_estimator=grpo,data.dataloader_num_workers=0,data.max_prompt_length=512,data.max_response_length=1024,data.train_batch_size=64,data.train_files=/home/Competition2025/P12/P12U007/data/gsm8k/train.parquet,data.val_files=/home/Competition2025/P12/P12U007/data/gsm8k/test.parquet,trainer.default_local_dir=/home/Competition2025/P12/P12U007/training/grpo_001/checkpoints,trainer.experiment_name=Qwen3_32B_SFT_MATH,trainer.logger=[console,wandb],trainer.n_gpus_per_node=8,trainer.nnodes=1,trainer.project_name=Qwen3_32B_SFT+GRPO,trainer.save_freq=50,trainer.test_freq=50,trainer.total_epochs=15
+    id: ???
+    num: ???
+    config_name: ppo_trainer
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.3'
+    cwd: /home/Competition2025/P12/P12U007/training/sft_Qwen3_math/checkpoints/global_step_116/huggingface
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /home/Competition2025/P12/P12U007/deps/verl/verl/trainer/config
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /home/Competition2025/P12/P12U007/training/sft_Qwen3_math/checkpoints/global_step_116/huggingface/outputs/2025-08-05/12-01-37
+    choices:
+      reward_model: dp_reward_model
+      critic: dp_critic
+      rollout@actor_rollout_ref.rollout: rollout
+      ref@actor_rollout_ref.ref: dp_ref
+      data: legacy_data
+      npu_profile@trainer.npu_profile: npu_profile
+      actor@actor_rollout_ref.actor: dp_actor
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: default
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

outputs/2025-08-05/12-01-37/.hydra/overrides.yaml

@@ -0,0 +1,31 @@
+- data.train_files=/home/Competition2025/P12/P12U007/data/gsm8k/train.parquet
+- data.val_files=/home/Competition2025/P12/P12U007/data/gsm8k/test.parquet
+- data.train_batch_size=64
+- data.max_prompt_length=512
+- data.max_response_length=1024
+- data.dataloader_num_workers=0
+- actor_rollout_ref.model.path=//home/Competition2025/P12/P12U007/training/sft_Qwen3_math/checkpoints/global_step_116/huggingface
+- actor_rollout_ref.model.use_remove_padding=True
+- actor_rollout_ref.actor.optim.lr=5e-7
+- actor_rollout_ref.actor.ppo_mini_batch_size=32
+- actor_rollout_ref.actor.ppo_micro_batch_size_per_gpu=2
+- actor_rollout_ref.actor.use_kl_loss=True
+- actor_rollout_ref.actor.kl_loss_coef=0.001
+- +actor_rollout_ref.actor.fsdp_config.model_dtype=bf16
+- +actor_rollout_ref.ref.fsdp_config.model_dtype=bf16
+- +actor_rollout_ref.model.attn_implementation=flash_attention_2
+- actor_rollout_ref.rollout.log_prob_micro_batch_size_per_gpu=4
+- actor_rollout_ref.rollout.tensor_model_parallel_size=4
+- actor_rollout_ref.rollout.gpu_memory_utilization=0.7
+- actor_rollout_ref.rollout.n=4
+- actor_rollout_ref.ref.log_prob_micro_batch_size_per_gpu=2
+- algorithm.adv_estimator=grpo
+- trainer.n_gpus_per_node=8
+- trainer.nnodes=1
+- trainer.save_freq=50
+- trainer.test_freq=50
+- trainer.default_local_dir=/home/Competition2025/P12/P12U007/training/grpo_001/checkpoints
+- trainer.logger=[console,wandb]
+- trainer.project_name=Qwen3_32B_SFT+GRPO
+- trainer.experiment_name=Qwen3_32B_SFT_MATH
+- trainer.total_epochs=15

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}