Hugging Face's logo

Fulcrum-AI
/
Ryze-Embed-4

Sentence Similarity
Transformers
Safetensors
English
qwen2
text-generation
mergekit
Merge
custom_code
text-generation-inference
text-embeddings-inference
Inference Endpoints
Model card Files Community
Fulcrum-AI commited on
Commit
722f226
·
verified ·
1 Parent(s): dd1227f

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. README.md +83 -0
  2. added_tokens.json +5 -0
  3. config.json +33 -0
  4. mergekit_config.yml +54 -0
  5. merges.txt +0 -0
  6. model-00001-of-00002.safetensors +3 -0
  7. model-00001-of-00003.safetensors +3 -0
  8. model-00002-of-00002.safetensors +3 -0
  9. model-00002-of-00003.safetensors +3 -0
  10. model-00003-of-00003.safetensors +3 -0
  11. model.safetensors.index.json +1 -0
  12. special_tokens_map.json +20 -0
  13. tokenizer.json +0 -0
  14. tokenizer_config.json +50 -0
  15. vocab.json +0 -0
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - Fulcrum-AI/Ryze-Embed-3
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+
9
+ ---
10
+ # merged
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
+ * [Fulcrum-AI/Ryze-Embed-3](https://huggingface.co/Fulcrum-AI/Ryze-Embed-3)
23
+
24
+ ### Configuration
25
+
26
+ The following YAML configuration was used to produce this model:
27
+
28
+ ```yaml
29
+ dtype: bfloat16
30
+ merge_method: passthrough
31
+ slices:
32
+ - sources:
33
+ - layer_range: [0, 6]
34
+ model: Fulcrum-AI/Ryze-Embed-3
35
+ - sources:
36
+ - layer_range: [3, 9]
37
+ model: Fulcrum-AI/Ryze-Embed-3
38
+ - sources:
39
+ - layer_range: [6, 12]
40
+ model: Fulcrum-AI/Ryze-Embed-3
41
+ - sources:
42
+ - layer_range: [9, 15]
43
+ model: Fulcrum-AI/Ryze-Embed-3
44
+ - sources:
45
+ - layer_range: [12, 18]
46
+ model: Fulcrum-AI/Ryze-Embed-3
47
+ - sources:
48
+ - layer_range: [15, 21]
49
+ model: Fulcrum-AI/Ryze-Embed-3
50
+ - sources:
51
+ - layer_range: [18, 24]
52
+ model: Fulcrum-AI/Ryze-Embed-3
53
+ - sources:
54
+ - layer_range: [21, 27]
55
+ model: Fulcrum-AI/Ryze-Embed-3
56
+ - sources:
57
+ - layer_range: [24, 30]
58
+ model: Fulcrum-AI/Ryze-Embed-3
59
+ - sources:
60
+ - layer_range: [27, 33]
61
+ model: Fulcrum-AI/Ryze-Embed-3
62
+ - sources:
63
+ - layer_range: [30, 36]
64
+ model: Fulcrum-AI/Ryze-Embed-3
65
+ - sources:
66
+ - layer_range: [33, 39]
67
+ model: Fulcrum-AI/Ryze-Embed-3
68
+ - sources:
69
+ - layer_range: [36, 42]
70
+ model: Fulcrum-AI/Ryze-Embed-3
71
+ - sources:
72
+ - layer_range: [39, 45]
73
+ model: Fulcrum-AI/Ryze-Embed-3
74
+ - sources:
75
+ - layer_range: [42, 48]
76
+ model: Fulcrum-AI/Ryze-Embed-3
77
+ - sources:
78
+ - layer_range: [45, 51]
79
+ model: Fulcrum-AI/Ryze-Embed-3
80
+ - sources:
81
+ - layer_range: [48, 52]
82
+ model: Fulcrum-AI/Ryze-Embed-3
83
+ ```
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Fulcrum-AI/Ryze-Embed-3",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoModel": "Alibaba-NLP/gte-Qwen2-1.5B-instruct--modeling_qwen.Qwen2Model",
9
+ "AutoModelForCausalLM": "Alibaba-NLP/gte-Qwen2-1.5B-instruct--modeling_qwen.Qwen2ForCausalLM",
10
+ "AutoModelForSequenceClassification": "Alibaba-NLP/gte-Qwen2-1.5B-instruct--modeling_qwen.Qwen2ForSequenceClassification"
11
+ },
12
+ "bos_token_id": 151643,
13
+ "eos_token_id": 151643,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 1536,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8960,
18
+ "max_position_embeddings": 131072,
19
+ "max_window_layers": 21,
20
+ "model_type": "qwen2",
21
+ "num_attention_heads": 12,
22
+ "num_hidden_layers": 100,
23
+ "num_key_value_heads": 2,
24
+ "rms_norm_eps": 1e-06,
25
+ "rope_theta": 1000000.0,
26
+ "sliding_window": 131072,
27
+ "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.42.4",
30
+ "use_cache": true,
31
+ "use_sliding_window": false,
32
+ "vocab_size": 151646
33
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ dtype: bfloat16
2
+ merge_method: passthrough
3
+ slices:
4
+ - sources:
5
+ - layer_range: [0, 6]
6
+ model: Fulcrum-AI/Ryze-Embed-3
7
+ - sources:
8
+ - layer_range: [3, 9]
9
+ model: Fulcrum-AI/Ryze-Embed-3
10
+ - sources:
11
+ - layer_range: [6, 12]
12
+ model: Fulcrum-AI/Ryze-Embed-3
13
+ - sources:
14
+ - layer_range: [9, 15]
15
+ model: Fulcrum-AI/Ryze-Embed-3
16
+ - sources:
17
+ - layer_range: [12, 18]
18
+ model: Fulcrum-AI/Ryze-Embed-3
19
+ - sources:
20
+ - layer_range: [15, 21]
21
+ model: Fulcrum-AI/Ryze-Embed-3
22
+ - sources:
23
+ - layer_range: [18, 24]
24
+ model: Fulcrum-AI/Ryze-Embed-3
25
+ - sources:
26
+ - layer_range: [21, 27]
27
+ model: Fulcrum-AI/Ryze-Embed-3
28
+ - sources:
29
+ - layer_range: [24, 30]
30
+ model: Fulcrum-AI/Ryze-Embed-3
31
+ - sources:
32
+ - layer_range: [27, 33]
33
+ model: Fulcrum-AI/Ryze-Embed-3
34
+ - sources:
35
+ - layer_range: [30, 36]
36
+ model: Fulcrum-AI/Ryze-Embed-3
37
+ - sources:
38
+ - layer_range: [33, 39]
39
+ model: Fulcrum-AI/Ryze-Embed-3
40
+ - sources:
41
+ - layer_range: [36, 42]
42
+ model: Fulcrum-AI/Ryze-Embed-3
43
+ - sources:
44
+ - layer_range: [39, 45]
45
+ model: Fulcrum-AI/Ryze-Embed-3
46
+ - sources:
47
+ - layer_range: [42, 48]
48
+ model: Fulcrum-AI/Ryze-Embed-3
49
+ - sources:
50
+ - layer_range: [45, 51]
51
+ model: Fulcrum-AI/Ryze-Embed-3
52
+ - sources:
53
+ - layer_range: [48, 52]
54
+ model: Fulcrum-AI/Ryze-Embed-3
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2adef72d908cc8c4ae3f0282996d8b8623bba9c83de6ac8601c696286a4573e
3
+ size 4972895520
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c309492c9ce38bd1c3dfa3d40cf6a393c8918606819939a10d8c8c89d8161832
3
+ size 4983916888
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a519b663243b5b77a36ef531d2f6ce4f65f54331296ea4a2ac1ead61fad4fa4
3
+ size 825865848
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:803f19b30653f857bf9ad6f50cf079ccf88da6c29a330686cf5d5eb76db796da
3
+ size 4988167232
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba92019842ab13ce499087c9d1721365246e19b4f618938086949d0a47173973
3
+ size 319334352
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.4", "total_size": 10291280896}, "weight_map": {"lm_head.weight": "model-00001-of-00003.safetensors", "model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.33.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.34.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.35.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.39.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.43.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.40.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.44.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.41.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.48.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.45.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.49.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.46.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.50.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.47.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.54.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.51.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.55.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.52.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.56.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.53.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00001-of-00003.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00001-of-00003.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00001-of-00003.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.60.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.57.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.61.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.58.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.62.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.59.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.66.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.63.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.67.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.64.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.68.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.65.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.72.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.69.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.73.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.70.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.74.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.71.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.78.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.75.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.79.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.76.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.80.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.77.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.84.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.81.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.84.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.84.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.84.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.85.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.82.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.85.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.85.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.85.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.86.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.83.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.86.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.86.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.86.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.90.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.87.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.90.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.87.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.90.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.87.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.90.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.87.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.91.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.88.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.91.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.88.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.91.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.88.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.91.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.88.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.92.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.89.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.92.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.89.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.92.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.89.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.92.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.89.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.96.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.93.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.96.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.93.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.96.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.93.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.96.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.93.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.97.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.94.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.97.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.94.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.97.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.94.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.97.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.94.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.98.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.95.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.98.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.95.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.98.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.95.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.98.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.95.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.99.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.99.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.99.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.99.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.norm.weight": "model-00003-of-00003.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_eos_token": true,
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
+ },
30
+ "additional_special_tokens": [
31
+ "<|im_start|>",
32
+ "<|im_end|>"
33
+ ],
34
+ "auto_map": {
35
+ "AutoTokenizer": [
36
+ "Alibaba-NLP/gte-Qwen2-1.5B-instruct--tokenization_qwen.Qwen2Tokenizer",
37
+ "Alibaba-NLP/gte-Qwen2-1.5B-instruct--tokenization_qwen.Qwen2TokenizerFast"
38
+ ]
39
+ },
40
+ "bos_token": null,
41
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
42
+ "clean_up_tokenization_spaces": false,
43
+ "eos_token": "<|endoftext|>",
44
+ "errors": "replace",
45
+ "model_max_length": 32768,
46
+ "pad_token": "<|endoftext|>",
47
+ "split_special_tokens": false,
48
+ "tokenizer_class": "Qwen2Tokenizer",
49
+ "unk_token": null
50
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff