Upload folder using huggingface_hub (#1)

- 4b3725ea7abf4b73fb2609978b8abfacacb35d4fae1c624d745e27d4a6522112 (8d30619b707e4077bda126e860eb6864c1ba1d67)
- 712ed0f6c40303945e0be0dd5ef4dab3bd658d149997498527e21911984fb8b5 (f313a31af3c114d37e9f536282436afd9ee899e1)
- 607f48aab62e24e34d26725b6d75fc26487a485dbba469cd1d2eb527c0fcfda1 (22419d868c96c94888d2aa51df3d32cc2add51e7)
- 3987420ab03abdb8c94eaa687e6ac2d86bf9b19a3bc84157899086814871baf5 (a5eb5d7b86b483cedec11a8a7d422c1fdc91d78a)
- 442dbb0647ec064b70076d8c926b9c59995a453936f63cb841ba7ac300ec0c42 (d6935af94da6795203604c074406bb82d6a321ec)
- bd37b7089a4d34376c006a84e90998c9532f5cb0187afecb06c4e01e49e4861c (c31bdeab4d18f6a6f4857d3e41e95711b857b741)
- 5f93b7776f30b3de8eccef3dbe7a58db0b9d70f11cd9b401b6917909098050b5 (e14cf1f117fdbaa5e02ac1db4699b4594ce55e08)
- 9c29f6ed902b37d7a313374e130a2e406ac9578e04e0dfdd475eeb929b3f9822 (d2b7fee45dce2a0b33251e0be1d4426c55104f5f)
- 728874f8f8df232bce743797a51d893cf5d40b30cfbf724c210d99aef5a2fc63 (dadaa62d0216f07ae9982d75ebc82ac5e6a6fe54)
- 31fa86db6949109622c9058d3defeb08421b2b5fb751386587080a6bd04a50e9 (3d972ca598610e799b562d0c5bc6f55204c3c378)
- 06484b6a7d13aa5b2f0028e2dba6cec0d2e9a7afa415e783bb8f8724f245ec1b (cd4d1710d39de66302fef314b6af06b6d07aaee6)
- 545af459253eac7c9932ce7815de85d66aab014764863af2dbf51ee4a4e69c6e (923e26d00a92b043785a429f5d8da75c7a8af390)
- 4da715652ee48ddc0b771ef439a175abbacdf16267d16c8a30ecc6b2790b7998 (138239c93110e26cbe696e6edfddf2eee29e3c47)
- bce140923f5e8ca5b2ab9f4d641a1a4848c0bcc5a18459c7c68b6e9f80cd0174 (cbc88935bb290f14d4d6f63bdf5ec5a005bfdd50)

README.md

@@ -0,0 +1,28 @@
+---
+base_model: Qwen/Qwen2.5-32B
+language:
+- en
+license: apache-2.0
+license_link: https://huggingface.co/Qwen/Qwen2.5-32B-Instruct/blob/main/LICENSE
+pipeline_tag: text-generation
+tags:
+- chat
+- mlx
+---
+
+# mlx-community/Qwen2.5-32B-Instruct-bf16
+
+The Model [mlx-community/Qwen2.5-32B-Instruct-bf16](https://huggingface.co/mlx-community/Qwen2.5-32B-Instruct-bf16) was converted to MLX format from [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct) using mlx-lm version **0.18.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Qwen2.5-32B-Instruct-bf16")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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 +1,27 @@
+{
+    "architectures": [
+        "Qwen2ForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 27648,
+    "max_position_embeddings": 32768,
+    "max_window_layers": 70,
+    "model_type": "qwen2",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sliding_window": 131072,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.43.1",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vocab_size": 152064
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b95cdf1b6350397fdeea670dfd55f8f6d60189980188d68694b548e2449fe29
+size 5174846606

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44b641a52b8d0c145a88074e7032b5a5c0935514b68b6407ca932a11f9fcd09
+size 5285039934

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82c26855df93925caa5178a2b88cf9549d6695eae6d2cf44f6dec80cf319883
+size 5159175019

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddadfeb00f7157dd6f0a594fd7b8e3bcab51884920aed136c2c882df4a6e20f
+size 5159175050

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72090a0893e3d4725506e91c3355118dd668eb3c3fcac5b83dfb24461933f138
+size 5285040006

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21bbe741688ac2f0ee198fa30475bf9f489da0a1e43cf497f1461b88ef5eb9b
+size 5159175038

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:720640bf78552b58239f4eafed7247c86a79489c7014748222e8082a6e2bb660
+size 5159175046

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18bc0275ec144162cf0ad6788263412c7099ddc3358f78ada1c419bdff1b73bf
+size 5285040004

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8895fbf83668b81c0d3de76edb56beca16ccd678d91cfcda4c9408f2a7edd4e7
+size 5159175048

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d5082de53c49fa7cf5b51241d23f3d7b7e863887105e59d1b5f0e2c32641d7
+size 5159175056

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8418d7e68bdcd7f118c350e64fc3707e27e916fc71748300b70ff9189b49ed0d
+size 5285039996

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6591997f44c3efcf8e703424bfe07b1c0d6716d68bd42212497683f4013c5ed7
+size 5159175034

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8501624b2e8998c3de826bdabe02540081f699b0668f8a05c2ed4ea8e80f62ab
+size 3098609681

model.safetensors.index.json

@@ -0,0 +1,778 @@
+{
+    "metadata": {
+        "total_size": 65527752704
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00013-of-00013.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00013.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00013.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+        "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00013.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+        "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00003-of-00013.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+        "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00003-of-00013.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+        "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00003-of-00013.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+        "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00003-of-00013.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+        "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00004-of-00013.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+        "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00013.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00004-of-00013.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+        "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00004-of-00013.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+        "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00004-of-00013.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+        "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00004-of-00013.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00013.safetensors",
+        "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.19.self_attn.k_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.19.self_attn.q_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.19.self_attn.v_proj.bias": "model-00004-of-00013.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00013.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00013.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00013.safetensors",
+        "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00013.safetensors",
+        "model.layers.24.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.24.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.24.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00006-of-00013.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+        "model.layers.25.self_attn.k_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.25.self_attn.q_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.25.self_attn.v_proj.bias": "model-00005-of-00013.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00013.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00006-of-00013.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+        "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00006-of-00013.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+        "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00006-of-00013.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+        "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00006-of-00013.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00013.safetensors",
+        "model.layers.29.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.29.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.29.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00013.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00013.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00007-of-00013.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+        "model.layers.30.self_attn.k_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.30.self_attn.q_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.30.self_attn.v_proj.bias": "model-00006-of-00013.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00013.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00007-of-00013.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+        "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00007-of-00013.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+        "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00007-of-00013.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+        "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00007-of-00013.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00013.safetensors",
+        "model.layers.34.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.34.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.34.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.35.self_attn.k_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.35.self_attn.q_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.35.self_attn.v_proj.bias": "model-00007-of-00013.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00013.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.39.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.39.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.39.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00013.safetensors",
+        "model.layers.40.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.40.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.40.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00009-of-00013.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+        "model.layers.41.self_attn.k_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.41.self_attn.q_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.41.self_attn.v_proj.bias": "model-00008-of-00013.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00013.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00009-of-00013.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+        "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00009-of-00013.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+        "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.44.input_layernorm.weight": "model-00009-of-00013.safetensors",
+        "model.layers.44.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.44.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+        "model.layers.44.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.44.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.44.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.45.input_layernorm.weight": "model-00009-of-00013.safetensors",
+        "model.layers.45.mlp.down_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.45.mlp.up_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00013.safetensors",
+        "model.layers.45.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.45.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.45.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.45.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.45.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.46.input_layernorm.weight": "model-00010-of-00013.safetensors",
+        "model.layers.46.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.46.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+        "model.layers.46.self_attn.k_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.46.self_attn.q_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.46.self_attn.v_proj.bias": "model-00009-of-00013.safetensors",
+        "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00013.safetensors",
+        "model.layers.47.input_layernorm.weight": "model-00010-of-00013.safetensors",
+        "model.layers.47.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.47.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+        "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.48.input_layernorm.weight": "model-00010-of-00013.safetensors",
+        "model.layers.48.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.48.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+        "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.49.input_layernorm.weight": "model-00010-of-00013.safetensors",
+        "model.layers.49.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.49.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.49.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.49.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+        "model.layers.49.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.49.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.49.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.50.input_layernorm.weight": "model-00010-of-00013.safetensors",
+        "model.layers.50.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.50.mlp.up_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.50.post_attention_layernorm.weight": "model-00010-of-00013.safetensors",
+        "model.layers.50.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.50.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.50.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.50.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.50.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.50.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.51.input_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.51.mlp.down_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.51.mlp.gate_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.51.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.51.self_attn.k_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.51.self_attn.k_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.51.self_attn.o_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.51.self_attn.q_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.51.self_attn.q_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.51.self_attn.v_proj.bias": "model-00010-of-00013.safetensors",
+        "model.layers.51.self_attn.v_proj.weight": "model-00010-of-00013.safetensors",
+        "model.layers.52.input_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.52.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.52.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.53.input_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.53.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.53.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.54.input_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.54.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.54.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.54.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.54.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.54.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.54.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.55.input_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.55.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.55.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.55.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.55.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.55.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.55.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.55.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.55.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.55.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.55.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.56.input_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.56.mlp.down_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.56.mlp.gate_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.56.mlp.up_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00013.safetensors",
+        "model.layers.56.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.56.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.56.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.56.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.56.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.56.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.56.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.57.input_layernorm.weight": "model-00012-of-00013.safetensors",
+        "model.layers.57.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.57.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+        "model.layers.57.self_attn.k_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.57.self_attn.q_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.57.self_attn.v_proj.bias": "model-00011-of-00013.safetensors",
+        "model.layers.57.self_attn.v_proj.weight": "model-00011-of-00013.safetensors",
+        "model.layers.58.input_layernorm.weight": "model-00012-of-00013.safetensors",
+        "model.layers.58.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.58.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.58.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+        "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.59.input_layernorm.weight": "model-00012-of-00013.safetensors",
+        "model.layers.59.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.59.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.59.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.59.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+        "model.layers.59.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.59.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.59.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.59.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.60.input_layernorm.weight": "model-00012-of-00013.safetensors",
+        "model.layers.60.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.60.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.60.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.60.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+        "model.layers.60.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.60.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.60.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.60.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.60.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.60.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.60.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.61.input_layernorm.weight": "model-00012-of-00013.safetensors",
+        "model.layers.61.mlp.down_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.61.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.61.mlp.up_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.61.post_attention_layernorm.weight": "model-00012-of-00013.safetensors",
+        "model.layers.61.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.61.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.61.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.61.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.61.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.61.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.61.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.62.input_layernorm.weight": "model-00013-of-00013.safetensors",
+        "model.layers.62.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+        "model.layers.62.mlp.gate_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.62.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
+        "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
+        "model.layers.62.self_attn.k_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.62.self_attn.k_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.62.self_attn.o_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.62.self_attn.q_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.62.self_attn.q_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.62.self_attn.v_proj.bias": "model-00012-of-00013.safetensors",
+        "model.layers.62.self_attn.v_proj.weight": "model-00012-of-00013.safetensors",
+        "model.layers.63.input_layernorm.weight": "model-00013-of-00013.safetensors",
+        "model.layers.63.mlp.down_proj.weight": "model-00013-of-00013.safetensors",
+        "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00013.safetensors",
+        "model.layers.63.mlp.up_proj.weight": "model-00013-of-00013.safetensors",
+        "model.layers.63.post_attention_layernorm.weight": "model-00013-of-00013.safetensors",
+        "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00013.safetensors",
+        "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00013.safetensors",
+        "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00013.safetensors",
+        "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00013.safetensors",
+        "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00013.safetensors",
+        "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00013.safetensors",
+        "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00013.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00013.safetensors",
+        "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00003-of-00013.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00003-of-00013.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00013.safetensors",
+        "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00013.safetensors",
+        "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00013.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00013.safetensors",
+        "model.norm.weight": "model-00013-of-00013.safetensors"
+    }
+}

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_config.json

@@ -0,0 +1,207 @@
+{
+  "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
+    }
+  },
+  "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    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\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    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.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{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}