DeL-TaiseiOzaki commited on
Commit
e7abc39
·
verified ·
1 Parent(s): d2141c0

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096
4
+ - LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-sft
5
+ - LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft-med-grpo
6
+ - LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft
7
+ - Qwen/Qwen3-32B
8
+ library_name: transformers
9
+ tags:
10
+ - mergekit
11
+ - merge
12
+
13
+ ---
14
+ # qwen32b_stem_output
15
+
16
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
17
+
18
+ ## Merge Details
19
+ ### Merge Method
20
+
21
+ This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Qwen/Qwen3-32B](https://huggingface.co/Qwen/Qwen3-32B) as a base.
22
+
23
+ ### Models Merged
24
+
25
+ The following models were included in the merge:
26
+ * [LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096)
27
+ * [LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-sft](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-sft)
28
+ * [LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft-med-grpo](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft-med-grpo)
29
+ * [LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft](https://huggingface.co/LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft)
30
+
31
+ ### Configuration
32
+
33
+ The following YAML configuration was used to produce this model:
34
+
35
+ ```yaml
36
+ models:
37
+ - model: Qwen/Qwen3-32B
38
+ - model: LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-sft
39
+ parameters:
40
+ density: 0.60
41
+ weight: 0.30
42
+ - model: LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft
43
+ parameters:
44
+ density: 0.60
45
+ weight: 0.25
46
+ - model: LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096
47
+ parameters:
48
+ density: 0.55
49
+ weight: 0.20
50
+ - model: LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft-med-grpo
51
+ parameters:
52
+ density: 0.50
53
+ weight: 0.10
54
+ - model: Qwen/Qwen3-32B
55
+ parameters:
56
+ density: 0.53
57
+ weight: 0.15
58
+ merge_method: dare_ties
59
+ base_model: Qwen/Qwen3-32B
60
+ parameters:
61
+ int8_mask: true
62
+ normalize: false
63
+ dtype: bfloat16
64
+ ```
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "head_dim": 128,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 25600,
14
+ "max_position_embeddings": 40960,
15
+ "max_window_layers": 64,
16
+ "model_type": "qwen3",
17
+ "num_attention_heads": 64,
18
+ "num_hidden_layers": 64,
19
+ "num_key_value_heads": 8,
20
+ "rms_norm_eps": 1e-06,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.52.3",
27
+ "use_cache": true,
28
+ "use_sliding_window": false,
29
+ "vocab_size": 151936
30
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ models:
2
+ - model: Qwen/Qwen3-32B
3
+ - model: LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-sft
4
+ parameters:
5
+ density: 0.60
6
+ weight: 0.30
7
+ - model: LLMcompe-Team-Watanabe/Qwen3-32B-openmathreasoning-sft
8
+ parameters:
9
+ density: 0.60
10
+ weight: 0.25
11
+ - model: LLMcompe-Team-Watanabe/Qwen3-32B-sft-HIS-Chem-Engineering-45k-1ep-lr5e6-4096
12
+ parameters:
13
+ density: 0.55
14
+ weight: 0.20
15
+ - model: LLMcompe-Team-Watanabe/Qwen3-32B-textbookreasoning-UGPhysics-AoPsInstruct-sft-med-grpo
16
+ parameters:
17
+ density: 0.50
18
+ weight: 0.10
19
+ - model: Qwen/Qwen3-32B
20
+ parameters:
21
+ density: 0.53
22
+ weight: 0.15
23
+ merge_method: dare_ties
24
+ base_model: Qwen/Qwen3-32B
25
+ parameters:
26
+ int8_mask: true
27
+ normalize: false
28
+ dtype: bfloat16
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2585bc925885092383e177881e608a87b047265f885f9da28f0f4bb8a5420f8
3
+ size 4967673312
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ef1490571a56b041673cb02b3be24d9adf77d14d68c77ea1b57e2b0957a386
3
+ size 4970372168
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16fb110b193380483bdeec1f5fe1a69a755589d6c606daa790153e143f93ac32
3
+ size 4875989744
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6de7bc4faf0fad0540ea82d4bb7a3db78e3d0462f0d0cab5d0c5d1ae9ee9b24c
3
+ size 4875989736
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fb70cce07e624a349794f761051ff2c1341b719f2c80872add332313dd44865
3
+ size 4875989744
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:713b0e9108b45822296a3e4ecb0ff774acbbb03d93bf73142ad3fab8b3c638ea
3
+ size 4875989736
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adcf3463baa9c00e7f6225bde59ef4e6281d4831481eef68c5d2c853045e18b1
3
+ size 4875989744
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:577c80c4fecc41bd801a9e994dc6297b1e06f42cd78c3766b50ead795128453e
3
+ size 4875989736
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:766a8293ed6fde2172b2249e6a8d578984914831d016ea8ba793390872982611
3
+ size 4875989744
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6dd2f9917668eb9177404020f0f018060550fdf6da3846f8781f287515ad60
3
+ size 4875989736
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d549e59eb9072f46033c5af090cdeb4c0440cc4b3a81cc1e78619f61aa3626d
3
+ size 4875989744
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13c6554015feada1710add6b0c7244f29d24052e7f68842d52f6ffd095ca586e
3
+ size 4875989736
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6716d507981e5853ddf8282d6005f1e1f21169c76f67078c387f339d8929653
3
+ size 4875989736
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee3e53101ec89672ed8894938466194fc36bf318e49ce23fced145f379d3103
3
+ size 1950395864
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.1.3"}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.k_norm.weight": "model-00003-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-00003-of-00014.safetensors", "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-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-00004-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.q_norm.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.k_norm.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-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-00004-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-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-00004-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.self_attn.q_norm.weight": "model-00004-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-00004-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.23.self_attn.q_norm.weight": "model-00004-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-00004-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.k_norm.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.q_norm.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.k_norm.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.q_norm.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.k_norm.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.q_norm.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.k_norm.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.q_norm.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.k_norm.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-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-00006-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.k_norm.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.q_norm.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.31.self_attn.k_norm.weight": "model-00006-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-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-00006-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.32.self_attn.k_norm.weight": "model-00006-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.32.self_attn.q_norm.weight": "model-00006-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-00006-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.k_norm.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.q_norm.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.k_norm.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.q_norm.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.35.self_attn.k_norm.weight": "model-00007-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.self_attn.q_norm.weight": "model-00007-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.36.self_attn.k_norm.weight": "model-00007-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.36.self_attn.q_norm.weight": "model-00007-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.37.self_attn.k_norm.weight": "model-00007-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.37.self_attn.q_norm.weight": "model-00007-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.k_norm.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.q_norm.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.k_norm.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.q_norm.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.4.self_attn.k_norm.weight": "model-00008-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-00008-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.40.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.40.self_attn.k_norm.weight": "model-00008-of-00014.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.40.self_attn.q_norm.weight": "model-00008-of-00014.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-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-00008-of-00014.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.41.self_attn.k_norm.weight": "model-00008-of-00014.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.41.self_attn.q_norm.weight": "model-00008-of-00014.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.k_norm.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.q_norm.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-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-00009-of-00014.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.q_norm.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.44.self_attn.k_norm.weight": "model-00009-of-00014.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.44.self_attn.q_norm.weight": "model-00009-of-00014.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.45.self_attn.k_norm.weight": "model-00009-of-00014.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00009-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-00009-of-00014.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.46.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.46.self_attn.k_norm.weight": "model-00009-of-00014.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.46.self_attn.q_norm.weight": "model-00009-of-00014.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.47.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.k_norm.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.q_norm.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.k_norm.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.q_norm.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.49.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.49.self_attn.k_norm.weight": "model-00010-of-00014.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.49.self_attn.q_norm.weight": "model-00010-of-00014.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.5.self_attn.k_norm.weight": "model-00010-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.5.self_attn.q_norm.weight": "model-00010-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.50.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00010-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-00010-of-00014.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.50.self_attn.q_norm.weight": "model-00010-of-00014.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.51.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.k_norm.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.q_norm.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.k_norm.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.q_norm.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.53.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.53.self_attn.k_norm.weight": "model-00011-of-00014.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.53.self_attn.q_norm.weight": "model-00011-of-00014.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.54.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.54.self_attn.k_norm.weight": "model-00011-of-00014.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.54.self_attn.q_norm.weight": "model-00011-of-00014.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.55.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.55.self_attn.k_norm.weight": "model-00011-of-00014.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.55.self_attn.q_norm.weight": "model-00011-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-00011-of-00014.safetensors", "model.layers.56.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.k_norm.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.q_norm.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.57.self_attn.k_norm.weight": "model-00012-of-00014.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.self_attn.q_norm.weight": "model-00012-of-00014.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.58.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.58.self_attn.k_norm.weight": "model-00012-of-00014.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.58.self_attn.q_norm.weight": "model-00012-of-00014.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.59.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00012-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-00012-of-00014.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.59.self_attn.q_norm.weight": "model-00012-of-00014.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.6.self_attn.k_norm.weight": "model-00012-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.self_attn.q_norm.weight": "model-00012-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.60.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.k_norm.weight": "model-00013-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-00013-of-00014.safetensors", "model.layers.60.self_attn.q_norm.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.61.self_attn.k_norm.weight": "model-00013-of-00014.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.61.self_attn.q_norm.weight": "model-00013-of-00014.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.62.self_attn.k_norm.weight": "model-00013-of-00014.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.62.self_attn.q_norm.weight": "model-00013-of-00014.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.63.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.63.self_attn.k_norm.weight": "model-00013-of-00014.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.63.self_attn.q_norm.weight": "model-00013-of-00014.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_norm.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.q_norm.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.k_norm.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.q_norm.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_norm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_norm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "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 %}",
231
+ "clean_up_tokenization_spaces": false,
232
+ "eos_token": "<|im_end|>",
233
+ "errors": "replace",
234
+ "model_max_length": 131072,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }