mlabonne commited on
Commit
420fcbc
1 Parent(s): 7a8cc25

Add files using upload-large-folder tool

Browse files
README.md ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-32B-Instruct
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merge
11
+
12
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
13
+
14
+ ## Merge Details
15
+ ### Merge Method
16
+
17
+ This model was merged using the passthrough merge method.
18
+
19
+ ### Models Merged
20
+
21
+ The following models were included in the merge:
22
+ * [Qwen/Qwen2.5-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-32B-Instruct)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ slices:
30
+ - sources:
31
+ - layer_range: [0, 16]
32
+ model: Qwen/Qwen2.5-32B-Instruct
33
+ - sources:
34
+ - layer_range: [8, 24]
35
+ model: Qwen/Qwen2.5-32B-Instruct
36
+ - sources:
37
+ - layer_range: [16, 32]
38
+ model: Qwen/Qwen2.5-32B-Instruct
39
+ - sources:
40
+ - layer_range: [24, 40]
41
+ model: Qwen/Qwen2.5-32B-Instruct
42
+ - sources:
43
+ - layer_range: [32, 48]
44
+ model: Qwen/Qwen2.5-32B-Instruct
45
+ - sources:
46
+ - layer_range: [40, 56]
47
+ model: Qwen/Qwen2.5-32B-Instruct
48
+ - sources:
49
+ - layer_range: [56, 64]
50
+ model: Qwen/Qwen2.5-32B-Instruct
51
+ merge_method: passthrough
52
+ dtype: bfloat16
53
+
54
+ ```
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 27648,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 70,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 104,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": null,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.44.2",
25
+ "use_cache": true,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 152064
28
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ slices:
2
+ - sources:
3
+ - layer_range: [0, 16]
4
+ model: Qwen/Qwen2.5-32B-Instruct
5
+ - sources:
6
+ - layer_range: [8, 24]
7
+ model: Qwen/Qwen2.5-32B-Instruct
8
+ - sources:
9
+ - layer_range: [16, 32]
10
+ model: Qwen/Qwen2.5-32B-Instruct
11
+ - sources:
12
+ - layer_range: [24, 40]
13
+ model: Qwen/Qwen2.5-32B-Instruct
14
+ - sources:
15
+ - layer_range: [32, 48]
16
+ model: Qwen/Qwen2.5-32B-Instruct
17
+ - sources:
18
+ - layer_range: [40, 56]
19
+ model: Qwen/Qwen2.5-32B-Instruct
20
+ - sources:
21
+ - layer_range: [56, 64]
22
+ model: Qwen/Qwen2.5-32B-Instruct
23
+ merge_method: passthrough
24
+ dtype: bfloat16
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74deab43bf4d1d06a666360a704fcc6b809e1775b866cb8f5c711aa57f285128
3
+ size 4949338472
model-00002-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2261aa527c1df243276cb568af3193530d1ad153c383de6d8f977e4c32d06eae
3
+ size 4865571360
model-00003-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dd13520fc7e5ae3c93d87107927e8eb7d115114a5f31233acea0ccb5abed5b2
3
+ size 4991417800
model-00004-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b172aa093706a61a4e3a712cc909d7dc91b13840b36b5815124c6d12575e32
3
+ size 4760701016
model-00005-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4de64d1225c6d82c3b212341ad893919a9a1d1e28c70128db53c704a91114ddc
3
+ size 4991417800
model-00006-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10df7bfda55e64bd2b741bbf27982d7e142b66901e21b31c52f28f2c7075dbcf
3
+ size 4886565968
model-00007-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def230bec4b48636d05903c5d5cc51c7ef1397e1821897c790a2f9093c2f59ae
3
+ size 4750194440
model-00008-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12baf4129372e6f9ae9cc94be82763acf382478649e4652c3e6742288fc1df1a
3
+ size 4991417800
model-00009-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f804d31ef155029477e0d40c18d37a4bd14c20d42537af82ae5c94cb8224a926
3
+ size 4760701016
model-00010-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ff0027160cbdfdac022536a3a310e4a3ed2408c99c82f1304f78dd02ed4352
3
+ size 4876059392
model-00011-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4247f30b0e2a61caaa2c7234b2a1444c1a6624a40694f584b916cc076aad733d
3
+ size 4991417800
model-00012-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56ab75430c128e046e81c823f1cbcdd95d795e01ba9827e11fb036523f275734
3
+ size 4760701016
model-00013-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd725fae66baaa47b5129a6d15c5a650d513f8d38b7acc8684a442da74b08af9
3
+ size 4991417800
model-00014-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:529fd591d7f19b98f5faee3cc852eebb188c074157e6adcc1991e85db6ad5346
3
+ size 4886565968
model-00015-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f67a214bd630f97cfde9f242c0a54abdcc2eb046d44dea3d987e49fde3cc4e8b
3
+ size 4750194440
model-00016-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a58310b807cfd1a0749a6938c48ad13ffb94971c583446b4ae615bfdbc65a4f
3
+ size 4991417800
model-00017-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71af7b359dabcf35850371b6ba9579ac46ea061c57624f549f022d6153eefbbb
3
+ size 4886555632
model-00018-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fae5eef69de198510d2b2271569da528c7700952472ec2f25203abb9c1f5a1d
3
+ size 4876059392
model-00019-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9665043870e1a668a6b92dc1c0a5d8b75b455debab22118c3e69ef44973ebae9
3
+ size 4876059408
model-00020-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d9ba2bd717fe359142287a49d3ca3cff37a13da7d1a2ad5dd902f1277af7255
3
+ size 4876059416
model-00021-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4a02eaef99a6ec440e74fc4dfe2c450a4f6a1ffb160e564fa491dafa9d9ac6
3
+ size 4876069760
model-00022-of-00022.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:420a94d576dbc9ebf89a89f9cc1e1b29201fb5926660f83aae303832360bba1f
3
+ size 1950413392
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 104536172544}, "weight_map": {"lm_head.weight": "model-00001-of-00022.safetensors", "model.embed_tokens.weight": "model-00001-of-00022.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00022.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00022.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00022.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00022.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00022.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00022.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00022.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00022.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00022.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00022.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00022.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00022.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00022.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00022.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00022.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00022.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00022.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00022.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00022.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00022.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00022.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00022.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00022.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00022.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00022.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00022.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00022.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00022.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00022.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00022.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00022.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00022.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00022.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00022.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00022.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00022.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00022.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00022.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00022.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00022.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00022.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00022.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00022.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00022.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00022.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00022.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00022.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00022.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00022.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00022.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00022.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00022.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00022.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00022.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00022.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00004-of-00022.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00004-of-00022.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00022.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00022.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00004-of-00022.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00004-of-00022.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00022.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00004-of-00022.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00004-of-00022.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00022.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00022.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00022.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00022.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00005-of-00022.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00005-of-00022.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00005-of-00022.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00005-of-00022.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00005-of-00022.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00005-of-00022.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00005-of-00022.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00005-of-00022.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00005-of-00022.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00005-of-00022.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00005-of-00022.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00005-of-00022.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00022.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00022.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00022.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00022.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00005-of-00022.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00005-of-00022.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00022.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00022.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00005-of-00022.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00005-of-00022.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00022.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00005-of-00022.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00005-of-00022.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00022.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00006-of-00022.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00006-of-00022.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00006-of-00022.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00006-of-00022.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00022.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00006-of-00022.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00022.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00006-of-00022.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00022.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00022.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00022.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00022.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00006-of-00022.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00006-of-00022.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00022.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00022.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00006-of-00022.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00006-of-00022.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00022.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00006-of-00022.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00006-of-00022.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00022.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00022.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00007-of-00022.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00022.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00007-of-00022.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00022.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00007-of-00022.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00022.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00007-of-00022.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00022.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00022.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00022.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00022.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00022.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00022.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00022.safetensors", "model.layers.48.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.40.input_layernorm.weight": "model-00007-of-00022.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00007-of-00022.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00007-of-00022.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00008-of-00022.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00008-of-00022.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00008-of-00022.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00008-of-00022.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00008-of-00022.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00008-of-00022.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.41.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00008-of-00022.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00008-of-00022.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00008-of-00022.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00008-of-00022.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00008-of-00022.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00008-of-00022.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.50.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.42.input_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00008-of-00022.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00022.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00008-of-00022.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00022.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00008-of-00022.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00008-of-00022.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00022.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00022.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00008-of-00022.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00008-of-00022.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00022.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00008-of-00022.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00008-of-00022.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00022.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.51.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00009-of-00022.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00022.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00009-of-00022.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00022.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00009-of-00022.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00022.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.52.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00009-of-00022.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00009-of-00022.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00009-of-00022.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00009-of-00022.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00009-of-00022.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00009-of-00022.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00009-of-00022.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00009-of-00022.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00009-of-00022.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00009-of-00022.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00009-of-00022.safetensors", "model.layers.53.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.45.input_layernorm.weight": "model-00009-of-00022.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00009-of-00022.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00009-of-00022.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00010-of-00022.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00022.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00010-of-00022.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00022.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00010-of-00022.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00022.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.3.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00010-of-00022.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00010-of-00022.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00010-of-00022.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.54.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00010-of-00022.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00010-of-00022.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00022.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00022.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00022.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00010-of-00022.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00022.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00022.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00010-of-00022.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00022.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00022.safetensors", "model.layers.55.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.47.input_layernorm.weight": "model-00010-of-00022.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00010-of-00022.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00022.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00011-of-00022.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00011-of-00022.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00011-of-00022.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00011-of-00022.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00011-of-00022.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00011-of-00022.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.64.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.56.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00011-of-00022.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00011-of-00022.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00011-of-00022.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00011-of-00022.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00011-of-00022.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00011-of-00022.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.65.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.57.input_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00011-of-00022.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00011-of-00022.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00011-of-00022.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00011-of-00022.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00011-of-00022.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00011-of-00022.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00011-of-00022.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00011-of-00022.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00011-of-00022.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00011-of-00022.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00011-of-00022.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00011-of-00022.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00011-of-00022.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00011-of-00022.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.66.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.58.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00012-of-00022.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00022.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00012-of-00022.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00022.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00012-of-00022.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00022.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.67.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.59.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00012-of-00022.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00012-of-00022.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00012-of-00022.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00012-of-00022.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00012-of-00022.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00012-of-00022.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00012-of-00022.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00012-of-00022.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00012-of-00022.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00012-of-00022.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00012-of-00022.safetensors", "model.layers.68.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.60.input_layernorm.weight": "model-00012-of-00022.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00012-of-00022.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00012-of-00022.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00013-of-00022.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00022.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00013-of-00022.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00022.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00013-of-00022.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00022.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.69.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.61.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00013-of-00022.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00022.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00013-of-00022.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00022.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00013-of-00022.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00022.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.70.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.62.input_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00013-of-00022.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00022.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00013-of-00022.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00022.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00013-of-00022.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00022.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00022.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00022.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00013-of-00022.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00022.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00022.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00013-of-00022.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00022.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00013-of-00022.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.71.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.63.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00014-of-00022.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00014-of-00022.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00014-of-00022.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00014-of-00022.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00014-of-00022.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00014-of-00022.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.4.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00014-of-00022.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00014-of-00022.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00014-of-00022.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.80.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.72.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00014-of-00022.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00014-of-00022.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00014-of-00022.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00014-of-00022.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00014-of-00022.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00014-of-00022.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00014-of-00022.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00014-of-00022.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00014-of-00022.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00014-of-00022.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00014-of-00022.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00014-of-00022.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00014-of-00022.safetensors", "model.layers.81.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.73.input_layernorm.weight": "model-00014-of-00022.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00015-of-00022.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00015-of-00022.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00015-of-00022.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00015-of-00022.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00015-of-00022.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00015-of-00022.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.82.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.74.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00015-of-00022.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00015-of-00022.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00015-of-00022.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00015-of-00022.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00015-of-00022.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00015-of-00022.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00015-of-00022.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00015-of-00022.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00015-of-00022.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00015-of-00022.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00015-of-00022.safetensors", "model.layers.83.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.75.input_layernorm.weight": "model-00015-of-00022.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00015-of-00022.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00015-of-00022.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00016-of-00022.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00016-of-00022.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00016-of-00022.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00016-of-00022.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00016-of-00022.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00016-of-00022.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.84.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.76.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.84.self_attn.k_proj.bias": "model-00016-of-00022.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00016-of-00022.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.84.self_attn.q_proj.bias": "model-00016-of-00022.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00016-of-00022.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.84.self_attn.v_proj.bias": "model-00016-of-00022.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00016-of-00022.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.85.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.77.input_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00016-of-00022.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00016-of-00022.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00016-of-00022.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00016-of-00022.safetensors", "model.layers.85.self_attn.k_proj.bias": "model-00016-of-00022.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00016-of-00022.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00016-of-00022.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00016-of-00022.safetensors", "model.layers.85.self_attn.q_proj.bias": "model-00016-of-00022.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00016-of-00022.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00016-of-00022.safetensors", "model.layers.85.self_attn.v_proj.bias": "model-00016-of-00022.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00016-of-00022.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00016-of-00022.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.86.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.78.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.86.self_attn.k_proj.bias": "model-00017-of-00022.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00017-of-00022.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.86.self_attn.q_proj.bias": "model-00017-of-00022.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00017-of-00022.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.86.self_attn.v_proj.bias": "model-00017-of-00022.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00017-of-00022.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.87.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.79.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.87.self_attn.k_proj.bias": "model-00017-of-00022.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00017-of-00022.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.87.self_attn.q_proj.bias": "model-00017-of-00022.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00017-of-00022.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.87.self_attn.v_proj.bias": "model-00017-of-00022.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00017-of-00022.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.88.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00017-of-00022.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00017-of-00022.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00017-of-00022.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.88.self_attn.k_proj.bias": "model-00017-of-00022.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00017-of-00022.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00017-of-00022.safetensors", "model.layers.88.self_attn.q_proj.bias": "model-00017-of-00022.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00017-of-00022.safetensors", "model.layers.88.self_attn.v_proj.bias": "model-00017-of-00022.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00017-of-00022.safetensors", "model.layers.89.input_layernorm.weight": "model-00017-of-00022.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.89.self_attn.k_proj.bias": "model-00018-of-00022.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.89.self_attn.q_proj.bias": "model-00018-of-00022.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.89.self_attn.v_proj.bias": "model-00018-of-00022.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.5.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00018-of-00022.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00018-of-00022.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00018-of-00022.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.90.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.90.self_attn.k_proj.bias": "model-00018-of-00022.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.90.self_attn.q_proj.bias": "model-00018-of-00022.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.90.self_attn.v_proj.bias": "model-00018-of-00022.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.91.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.91.self_attn.k_proj.bias": "model-00018-of-00022.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.91.self_attn.q_proj.bias": "model-00018-of-00022.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.91.self_attn.v_proj.bias": "model-00018-of-00022.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.92.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00018-of-00022.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00018-of-00022.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00018-of-00022.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.92.self_attn.k_proj.bias": "model-00018-of-00022.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00018-of-00022.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00018-of-00022.safetensors", "model.layers.92.self_attn.q_proj.bias": "model-00018-of-00022.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00018-of-00022.safetensors", "model.layers.92.self_attn.v_proj.bias": "model-00018-of-00022.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00018-of-00022.safetensors", "model.layers.93.input_layernorm.weight": "model-00018-of-00022.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.93.self_attn.k_proj.bias": "model-00019-of-00022.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.93.self_attn.q_proj.bias": "model-00019-of-00022.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.93.self_attn.v_proj.bias": "model-00019-of-00022.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.94.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.94.self_attn.k_proj.bias": "model-00019-of-00022.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.94.self_attn.q_proj.bias": "model-00019-of-00022.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.94.self_attn.v_proj.bias": "model-00019-of-00022.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.95.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.95.self_attn.k_proj.bias": "model-00019-of-00022.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.95.self_attn.q_proj.bias": "model-00019-of-00022.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.95.self_attn.v_proj.bias": "model-00019-of-00022.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.96.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.96.self_attn.k_proj.bias": "model-00019-of-00022.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.96.self_attn.q_proj.bias": "model-00019-of-00022.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.96.self_attn.v_proj.bias": "model-00019-of-00022.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.97.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00019-of-00022.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00019-of-00022.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00019-of-00022.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.97.self_attn.k_proj.bias": "model-00019-of-00022.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00019-of-00022.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00019-of-00022.safetensors", "model.layers.97.self_attn.q_proj.bias": "model-00019-of-00022.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00019-of-00022.safetensors", "model.layers.97.self_attn.v_proj.bias": "model-00019-of-00022.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00019-of-00022.safetensors", "model.layers.98.input_layernorm.weight": "model-00019-of-00022.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.98.self_attn.k_proj.bias": "model-00020-of-00022.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.98.self_attn.q_proj.bias": "model-00020-of-00022.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.98.self_attn.v_proj.bias": "model-00020-of-00022.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.99.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.99.self_attn.k_proj.bias": "model-00020-of-00022.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.99.self_attn.q_proj.bias": "model-00020-of-00022.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.99.self_attn.v_proj.bias": "model-00020-of-00022.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00020-of-00022.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.100.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.100.self_attn.k_proj.bias": "model-00020-of-00022.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.100.self_attn.q_proj.bias": "model-00020-of-00022.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.100.self_attn.v_proj.bias": "model-00020-of-00022.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.101.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00020-of-00022.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00020-of-00022.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00020-of-00022.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.101.self_attn.k_proj.bias": "model-00020-of-00022.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00020-of-00022.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00020-of-00022.safetensors", "model.layers.101.self_attn.q_proj.bias": "model-00020-of-00022.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00020-of-00022.safetensors", "model.layers.101.self_attn.v_proj.bias": "model-00020-of-00022.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00020-of-00022.safetensors", "model.layers.102.input_layernorm.weight": "model-00020-of-00022.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.102.self_attn.k_proj.bias": "model-00021-of-00022.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.102.self_attn.q_proj.bias": "model-00021-of-00022.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.102.self_attn.v_proj.bias": "model-00021-of-00022.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.103.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.103.self_attn.k_proj.bias": "model-00021-of-00022.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.103.self_attn.q_proj.bias": "model-00021-of-00022.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.103.self_attn.v_proj.bias": "model-00021-of-00022.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00021-of-00022.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.16.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.8.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00021-of-00022.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00021-of-00022.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00021-of-00022.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00021-of-00022.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00021-of-00022.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00021-of-00022.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00021-of-00022.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00021-of-00022.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00021-of-00022.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00021-of-00022.safetensors", "model.layers.17.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.9.input_layernorm.weight": "model-00021-of-00022.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00022-of-00022.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00022-of-00022.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00022-of-00022.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00022-of-00022.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00022-of-00022.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00022-of-00022.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00022-of-00022.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00022-of-00022.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00022-of-00022.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00022-of-00022.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00022-of-00022.safetensors", "model.norm.weight": "model-00022-of-00022.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "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",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff