Hugging Face's logo

mlx-community
/
Master-Yi-9B-8bit

MLX
Safetensors
llama
Model card Files Community
1

[WIP] Upload folder using huggingface_hub (multi-commit 2524deb714b2c0a4d5df96eadf0282c0ce385d4e49835ef113175c84c0eaa964)

#1
by prince-canuma - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+0
-175427
Files changed (9) hide show
  1. README.md +0 -22
  2. config.json +0 -32
  3. model-00001-of-00002.safetensors +0 -3
  4. model-00002-of-00002.safetensors +0 -3
  5. model.safetensors.index.json +0 -1118
  6. special_tokens_map.json +0 -33
  7. tokenizer.json +0 -0
  8. tokenizer.model +0 -3
  9. tokenizer_config.json +0 -61
README.md DELETED
@@ -1,22 +0,0 @@
1
- ---
2
- license: apache-2.0
3
- tags:
4
- - mlx
5
- ---
6
-
7
- # mlx-community/Master-Yi-9B-8bit
8
-
9
- The Model [mlx-community/Master-Yi-9B-8bit](https://huggingface.co/mlx-community/Master-Yi-9B-8bit) was converted to MLX format from [qnguyen3/Master-Yi-9B](https://huggingface.co/qnguyen3/Master-Yi-9B) using mlx-lm version **0.13.0**.
10
-
11
- ## Use with mlx
12
-
13
- ```bash
14
- pip install mlx-lm
15
- ```
16
-
17
- ```python
18
- from mlx_lm import load, generate
19
-
20
- model, tokenizer = load("mlx-community/Master-Yi-9B-8bit")
21
- response = generate(model, tokenizer, prompt="hello", verbose=True)
22
- ```
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 7,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 11008,
13
- "max_position_embeddings": 4096,
14
- "model_type": "llama",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 48,
17
- "num_key_value_heads": 4,
18
- "pad_token_id": 0,
19
- "pretraining_tp": 1,
20
- "quantization": {
21
- "group_size": 64,
22
- "bits": 8
23
- },
24
- "rms_norm_eps": 1e-06,
25
- "rope_scaling": null,
26
- "rope_theta": 5000000.0,
27
- "tie_word_embeddings": false,
28
- "torch_dtype": "bfloat16",
29
- "transformers_version": "4.40.1",
30
- "use_cache": true,
31
- "vocab_size": 64000
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ba118545eb899b6ff9c51d1aa347d1a24a902df1b6dd182498e605b0c0f09e0
3
- size 5330426736
 
 
 
 
model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:de25b1dffa4760b0e986386aa51ca3861f3adfcacf7bf1a1e0b56c264f085ce1
3
- size 4051317077
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,1118 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 9381617664
4
- },
5
- "weight_map": {
6
- "lm_head.biases": "model-00002-of-00002.safetensors",
7
- "lm_head.scales": "model-00002-of-00002.safetensors",
8
- "lm_head.weight": "model-00002-of-00002.safetensors",
9
- "model.embed_tokens.biases": "model-00001-of-00002.safetensors",
10
- "model.embed_tokens.scales": "model-00001-of-00002.safetensors",
11
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
12
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
14
- "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
15
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
17
- "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
18
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
19
- "model.layers.0.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
20
- "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
21
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
22
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.0.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
24
- "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
25
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
- "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
27
- "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
28
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
29
- "model.layers.0.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
30
- "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
31
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
32
- "model.layers.0.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
33
- "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
34
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
- "model.layers.1.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
37
- "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
38
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
39
- "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
40
- "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
41
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
42
- "model.layers.1.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
43
- "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
44
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
- "model.layers.1.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
47
- "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
48
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
- "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
50
- "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
51
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
- "model.layers.1.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
53
- "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
54
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
55
- "model.layers.1.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
56
- "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
57
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
58
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.10.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
60
- "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
61
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
62
- "model.layers.10.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
63
- "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
64
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
- "model.layers.10.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
66
- "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
67
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
68
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
69
- "model.layers.10.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
70
- "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
71
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
72
- "model.layers.10.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
73
- "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
74
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
75
- "model.layers.10.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
76
- "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
77
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
- "model.layers.10.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
79
- "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
80
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
81
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
82
- "model.layers.11.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
83
- "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
84
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
85
- "model.layers.11.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
86
- "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
87
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.11.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
89
- "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
90
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
91
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
92
- "model.layers.11.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
93
- "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
94
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
- "model.layers.11.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
96
- "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
97
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
98
- "model.layers.11.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
99
- "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
100
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
101
- "model.layers.11.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
102
- "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
103
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.12.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
106
- "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
107
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
- "model.layers.12.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
109
- "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
110
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
111
- "model.layers.12.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
112
- "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
113
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
114
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
115
- "model.layers.12.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
116
- "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
117
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
118
- "model.layers.12.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
119
- "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
120
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
121
- "model.layers.12.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
122
- "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
123
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
- "model.layers.12.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
125
- "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
126
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
127
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
128
- "model.layers.13.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
129
- "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
130
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
131
- "model.layers.13.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
132
- "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
133
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
134
- "model.layers.13.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
135
- "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
136
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
137
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
138
- "model.layers.13.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
139
- "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
140
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
141
- "model.layers.13.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
142
- "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
143
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
144
- "model.layers.13.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
145
- "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
146
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
147
- "model.layers.13.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
148
- "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
149
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
150
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
151
- "model.layers.14.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
152
- "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
153
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
- "model.layers.14.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
155
- "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
156
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
157
- "model.layers.14.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
158
- "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
159
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
160
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
161
- "model.layers.14.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
162
- "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
163
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
164
- "model.layers.14.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
165
- "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
166
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
167
- "model.layers.14.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
168
- "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
169
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
170
- "model.layers.14.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
171
- "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
172
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
173
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
174
- "model.layers.15.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
175
- "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
176
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
177
- "model.layers.15.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
178
- "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
179
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
180
- "model.layers.15.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
181
- "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
182
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
183
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
184
- "model.layers.15.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
185
- "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
186
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
187
- "model.layers.15.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
188
- "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
189
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
190
- "model.layers.15.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
191
- "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
192
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
193
- "model.layers.15.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
194
- "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
195
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
196
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
197
- "model.layers.16.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
198
- "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
199
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
200
- "model.layers.16.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
201
- "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
202
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
203
- "model.layers.16.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
204
- "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
205
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
206
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
207
- "model.layers.16.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
208
- "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
209
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
210
- "model.layers.16.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
211
- "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
212
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
213
- "model.layers.16.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
214
- "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
215
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
216
- "model.layers.16.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
217
- "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
218
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
219
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
220
- "model.layers.17.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
221
- "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
222
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
223
- "model.layers.17.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
224
- "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
225
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
226
- "model.layers.17.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
227
- "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
228
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
229
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
230
- "model.layers.17.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
231
- "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
232
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
233
- "model.layers.17.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
234
- "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
235
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
236
- "model.layers.17.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
237
- "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
238
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
239
- "model.layers.17.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
240
- "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
241
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
242
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
- "model.layers.18.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
244
- "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
245
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
246
- "model.layers.18.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
247
- "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
248
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
249
- "model.layers.18.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
250
- "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
251
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
252
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
253
- "model.layers.18.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
254
- "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
255
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
256
- "model.layers.18.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
257
- "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
258
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
259
- "model.layers.18.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
260
- "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
261
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
262
- "model.layers.18.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
263
- "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
264
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
265
- "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
266
- "model.layers.19.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
267
- "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
268
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
269
- "model.layers.19.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
270
- "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
271
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
272
- "model.layers.19.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
273
- "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
274
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
275
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
276
- "model.layers.19.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
277
- "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
278
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
279
- "model.layers.19.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
280
- "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
281
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
282
- "model.layers.19.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
283
- "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
284
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
285
- "model.layers.19.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
286
- "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
287
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
288
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
289
- "model.layers.2.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
290
- "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
291
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
292
- "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
293
- "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
294
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
295
- "model.layers.2.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
296
- "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
297
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
298
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
299
- "model.layers.2.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
300
- "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
301
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
302
- "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
303
- "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
304
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
305
- "model.layers.2.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
306
- "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
307
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
308
- "model.layers.2.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
309
- "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
310
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
311
- "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
312
- "model.layers.20.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
313
- "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
314
- "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
315
- "model.layers.20.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
316
- "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
317
- "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
318
- "model.layers.20.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
319
- "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
320
- "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
321
- "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
322
- "model.layers.20.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
323
- "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
324
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
325
- "model.layers.20.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
326
- "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
327
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
328
- "model.layers.20.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
329
- "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
330
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
331
- "model.layers.20.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
332
- "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
333
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
334
- "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
335
- "model.layers.21.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
336
- "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
337
- "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
338
- "model.layers.21.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
339
- "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
340
- "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
341
- "model.layers.21.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
342
- "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
343
- "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
344
- "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
345
- "model.layers.21.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
346
- "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
347
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
348
- "model.layers.21.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
349
- "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
350
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
351
- "model.layers.21.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
352
- "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
353
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
354
- "model.layers.21.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
355
- "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
356
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
357
- "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
358
- "model.layers.22.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
359
- "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
360
- "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
361
- "model.layers.22.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
362
- "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
363
- "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
364
- "model.layers.22.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
365
- "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
366
- "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
367
- "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
368
- "model.layers.22.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
369
- "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
370
- "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
371
- "model.layers.22.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
372
- "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
373
- "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
374
- "model.layers.22.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
375
- "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
376
- "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
377
- "model.layers.22.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
378
- "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
379
- "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
380
- "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
381
- "model.layers.23.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
382
- "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
383
- "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
384
- "model.layers.23.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
385
- "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
386
- "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
387
- "model.layers.23.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
388
- "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
389
- "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
390
- "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
391
- "model.layers.23.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
392
- "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
393
- "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
394
- "model.layers.23.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
395
- "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
396
- "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
397
- "model.layers.23.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
398
- "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
399
- "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
400
- "model.layers.23.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
401
- "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
402
- "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
403
- "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
404
- "model.layers.24.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
405
- "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
406
- "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
407
- "model.layers.24.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
408
- "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
409
- "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
410
- "model.layers.24.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
411
- "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
412
- "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
413
- "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
414
- "model.layers.24.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
415
- "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
416
- "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
417
- "model.layers.24.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
418
- "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
419
- "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
420
- "model.layers.24.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
421
- "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
422
- "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
423
- "model.layers.24.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
424
- "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
425
- "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
426
- "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
427
- "model.layers.25.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
428
- "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
429
- "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
430
- "model.layers.25.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
431
- "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
432
- "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
433
- "model.layers.25.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
434
- "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
435
- "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
436
- "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
437
- "model.layers.25.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
438
- "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
439
- "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
440
- "model.layers.25.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
441
- "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
442
- "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
443
- "model.layers.25.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
444
- "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
445
- "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
446
- "model.layers.25.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
447
- "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
448
- "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
449
- "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
450
- "model.layers.26.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
451
- "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
452
- "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
453
- "model.layers.26.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
454
- "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
455
- "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
456
- "model.layers.26.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
457
- "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
458
- "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
459
- "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
460
- "model.layers.26.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
461
- "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
462
- "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
463
- "model.layers.26.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
464
- "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
465
- "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
466
- "model.layers.26.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
467
- "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
468
- "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
469
- "model.layers.26.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
470
- "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
471
- "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
472
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
473
- "model.layers.27.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
474
- "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
475
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
476
- "model.layers.27.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
477
- "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
478
- "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
479
- "model.layers.27.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
480
- "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
481
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
482
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
483
- "model.layers.27.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
484
- "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
485
- "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
486
- "model.layers.27.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
487
- "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
488
- "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
489
- "model.layers.27.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
490
- "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
491
- "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
492
- "model.layers.27.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
493
- "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
494
- "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
495
- "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
496
- "model.layers.28.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
497
- "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
498
- "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
499
- "model.layers.28.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
500
- "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
501
- "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
502
- "model.layers.28.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
503
- "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
504
- "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
505
- "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
506
- "model.layers.28.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
507
- "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
508
- "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
509
- "model.layers.28.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
510
- "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
511
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
512
- "model.layers.28.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
513
- "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
514
- "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
515
- "model.layers.28.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
516
- "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
517
- "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
518
- "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
519
- "model.layers.29.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
520
- "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
521
- "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
522
- "model.layers.29.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
523
- "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
524
- "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
525
- "model.layers.29.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
526
- "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
527
- "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
528
- "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
529
- "model.layers.29.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
530
- "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
531
- "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
532
- "model.layers.29.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
533
- "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
534
- "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
535
- "model.layers.29.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
536
- "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
537
- "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
538
- "model.layers.29.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
539
- "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
540
- "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
541
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
542
- "model.layers.3.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
543
- "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
544
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
545
- "model.layers.3.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
546
- "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
547
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
548
- "model.layers.3.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
549
- "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
550
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
551
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
552
- "model.layers.3.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
553
- "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
554
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
555
- "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
556
- "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
557
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
558
- "model.layers.3.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
559
- "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
560
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
561
- "model.layers.3.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
562
- "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
563
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
564
- "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
565
- "model.layers.30.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
566
- "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
567
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
568
- "model.layers.30.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
569
- "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
570
- "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
571
- "model.layers.30.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
572
- "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
573
- "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
574
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
575
- "model.layers.30.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
576
- "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
577
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
578
- "model.layers.30.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
579
- "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
580
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
581
- "model.layers.30.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
582
- "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
583
- "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
584
- "model.layers.30.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
585
- "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
586
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
587
- "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
588
- "model.layers.31.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
589
- "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
590
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
591
- "model.layers.31.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
592
- "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
593
- "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
594
- "model.layers.31.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
595
- "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
596
- "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
597
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
598
- "model.layers.31.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
599
- "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
600
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
601
- "model.layers.31.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
602
- "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
603
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
604
- "model.layers.31.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
605
- "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
606
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
607
- "model.layers.31.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
608
- "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
609
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
610
- "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
611
- "model.layers.32.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
612
- "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
613
- "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
614
- "model.layers.32.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
615
- "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
616
- "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
617
- "model.layers.32.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
618
- "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
619
- "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
620
- "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
621
- "model.layers.32.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
622
- "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
623
- "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
624
- "model.layers.32.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
625
- "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
626
- "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
627
- "model.layers.32.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
628
- "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
629
- "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
630
- "model.layers.32.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
631
- "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
632
- "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
633
- "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
634
- "model.layers.33.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
635
- "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
636
- "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
637
- "model.layers.33.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
638
- "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
639
- "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
640
- "model.layers.33.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
641
- "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
642
- "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
643
- "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
644
- "model.layers.33.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
645
- "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
646
- "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
647
- "model.layers.33.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
648
- "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
649
- "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
650
- "model.layers.33.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
651
- "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
652
- "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
653
- "model.layers.33.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
654
- "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
655
- "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
656
- "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
657
- "model.layers.34.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
658
- "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
659
- "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
660
- "model.layers.34.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
661
- "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
662
- "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
663
- "model.layers.34.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
664
- "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
665
- "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
666
- "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
667
- "model.layers.34.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
668
- "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
669
- "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
670
- "model.layers.34.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
671
- "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
672
- "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
673
- "model.layers.34.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
674
- "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
675
- "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
676
- "model.layers.34.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
677
- "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
678
- "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
679
- "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
680
- "model.layers.35.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
681
- "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
682
- "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
683
- "model.layers.35.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
684
- "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
685
- "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
686
- "model.layers.35.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
687
- "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
688
- "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
689
- "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
690
- "model.layers.35.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
691
- "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
692
- "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
693
- "model.layers.35.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
694
- "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
695
- "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
696
- "model.layers.35.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
697
- "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
698
- "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
699
- "model.layers.35.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
700
- "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
701
- "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
702
- "model.layers.36.input_layernorm.weight": "model-00002-of-00002.safetensors",
703
- "model.layers.36.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
704
- "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
705
- "model.layers.36.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
706
- "model.layers.36.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
707
- "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
708
- "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
709
- "model.layers.36.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
710
- "model.layers.36.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
711
- "model.layers.36.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
712
- "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
713
- "model.layers.36.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
714
- "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
715
- "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
716
- "model.layers.36.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
717
- "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
718
- "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
719
- "model.layers.36.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
720
- "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
721
- "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
722
- "model.layers.36.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
723
- "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
724
- "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
725
- "model.layers.37.input_layernorm.weight": "model-00002-of-00002.safetensors",
726
- "model.layers.37.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
727
- "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
728
- "model.layers.37.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
729
- "model.layers.37.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
730
- "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
731
- "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
732
- "model.layers.37.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
733
- "model.layers.37.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
734
- "model.layers.37.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
735
- "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
736
- "model.layers.37.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
737
- "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
738
- "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
739
- "model.layers.37.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
740
- "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
741
- "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
742
- "model.layers.37.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
743
- "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
744
- "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
745
- "model.layers.37.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
746
- "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
747
- "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
748
- "model.layers.38.input_layernorm.weight": "model-00002-of-00002.safetensors",
749
- "model.layers.38.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
750
- "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
751
- "model.layers.38.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
752
- "model.layers.38.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
753
- "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
754
- "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
755
- "model.layers.38.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
756
- "model.layers.38.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
757
- "model.layers.38.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
758
- "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
759
- "model.layers.38.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
760
- "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
761
- "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
762
- "model.layers.38.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
763
- "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
764
- "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
765
- "model.layers.38.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
766
- "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
767
- "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
768
- "model.layers.38.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
769
- "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
770
- "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
771
- "model.layers.39.input_layernorm.weight": "model-00002-of-00002.safetensors",
772
- "model.layers.39.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
773
- "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
774
- "model.layers.39.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
775
- "model.layers.39.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
776
- "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
777
- "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
778
- "model.layers.39.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
779
- "model.layers.39.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
780
- "model.layers.39.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
781
- "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
782
- "model.layers.39.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
783
- "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
784
- "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
785
- "model.layers.39.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
786
- "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
787
- "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
788
- "model.layers.39.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
789
- "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
790
- "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
791
- "model.layers.39.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
792
- "model.layers.39.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
793
- "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
794
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
795
- "model.layers.4.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
796
- "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
797
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
798
- "model.layers.4.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
799
- "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
800
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
801
- "model.layers.4.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
802
- "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
803
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
804
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
805
- "model.layers.4.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
806
- "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
807
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
808
- "model.layers.4.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
809
- "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
810
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
811
- "model.layers.4.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
812
- "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
813
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
814
- "model.layers.4.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
815
- "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
816
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
817
- "model.layers.40.input_layernorm.weight": "model-00002-of-00002.safetensors",
818
- "model.layers.40.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
819
- "model.layers.40.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
820
- "model.layers.40.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
821
- "model.layers.40.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
822
- "model.layers.40.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
823
- "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
824
- "model.layers.40.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
825
- "model.layers.40.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
826
- "model.layers.40.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
827
- "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
828
- "model.layers.40.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
829
- "model.layers.40.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
830
- "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
831
- "model.layers.40.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
832
- "model.layers.40.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
833
- "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
834
- "model.layers.40.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
835
- "model.layers.40.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
836
- "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
837
- "model.layers.40.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
838
- "model.layers.40.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
839
- "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
840
- "model.layers.41.input_layernorm.weight": "model-00002-of-00002.safetensors",
841
- "model.layers.41.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
842
- "model.layers.41.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
843
- "model.layers.41.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
844
- "model.layers.41.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
845
- "model.layers.41.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
846
- "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
847
- "model.layers.41.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
848
- "model.layers.41.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
849
- "model.layers.41.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
850
- "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
851
- "model.layers.41.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
852
- "model.layers.41.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
853
- "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
854
- "model.layers.41.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
855
- "model.layers.41.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
856
- "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
857
- "model.layers.41.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
858
- "model.layers.41.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
859
- "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
860
- "model.layers.41.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
861
- "model.layers.41.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
862
- "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
863
- "model.layers.42.input_layernorm.weight": "model-00002-of-00002.safetensors",
864
- "model.layers.42.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
865
- "model.layers.42.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
866
- "model.layers.42.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
867
- "model.layers.42.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
868
- "model.layers.42.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
869
- "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
870
- "model.layers.42.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
871
- "model.layers.42.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
872
- "model.layers.42.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
873
- "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
874
- "model.layers.42.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
875
- "model.layers.42.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
876
- "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
877
- "model.layers.42.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
878
- "model.layers.42.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
879
- "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
880
- "model.layers.42.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
881
- "model.layers.42.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
882
- "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
883
- "model.layers.42.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
884
- "model.layers.42.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
885
- "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
886
- "model.layers.43.input_layernorm.weight": "model-00002-of-00002.safetensors",
887
- "model.layers.43.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
888
- "model.layers.43.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
889
- "model.layers.43.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
890
- "model.layers.43.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
891
- "model.layers.43.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
892
- "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
893
- "model.layers.43.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
894
- "model.layers.43.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
895
- "model.layers.43.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
896
- "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
897
- "model.layers.43.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
898
- "model.layers.43.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
899
- "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
900
- "model.layers.43.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
901
- "model.layers.43.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
902
- "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
903
- "model.layers.43.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
904
- "model.layers.43.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
905
- "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
906
- "model.layers.43.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
907
- "model.layers.43.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
908
- "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
909
- "model.layers.44.input_layernorm.weight": "model-00002-of-00002.safetensors",
910
- "model.layers.44.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
911
- "model.layers.44.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
912
- "model.layers.44.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
913
- "model.layers.44.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
914
- "model.layers.44.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
915
- "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
916
- "model.layers.44.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
917
- "model.layers.44.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
918
- "model.layers.44.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
919
- "model.layers.44.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
920
- "model.layers.44.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
921
- "model.layers.44.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
922
- "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
923
- "model.layers.44.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
924
- "model.layers.44.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
925
- "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
926
- "model.layers.44.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
927
- "model.layers.44.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
928
- "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
929
- "model.layers.44.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
930
- "model.layers.44.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
931
- "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
932
- "model.layers.45.input_layernorm.weight": "model-00002-of-00002.safetensors",
933
- "model.layers.45.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
934
- "model.layers.45.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
935
- "model.layers.45.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
936
- "model.layers.45.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
937
- "model.layers.45.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
938
- "model.layers.45.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
939
- "model.layers.45.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
940
- "model.layers.45.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
941
- "model.layers.45.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
942
- "model.layers.45.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
943
- "model.layers.45.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
944
- "model.layers.45.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
945
- "model.layers.45.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
946
- "model.layers.45.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
947
- "model.layers.45.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
948
- "model.layers.45.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
949
- "model.layers.45.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
950
- "model.layers.45.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
951
- "model.layers.45.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
952
- "model.layers.45.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
953
- "model.layers.45.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
954
- "model.layers.45.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
955
- "model.layers.46.input_layernorm.weight": "model-00002-of-00002.safetensors",
956
- "model.layers.46.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
957
- "model.layers.46.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
958
- "model.layers.46.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
959
- "model.layers.46.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
960
- "model.layers.46.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
961
- "model.layers.46.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
962
- "model.layers.46.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
963
- "model.layers.46.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
964
- "model.layers.46.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
965
- "model.layers.46.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
966
- "model.layers.46.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
967
- "model.layers.46.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
968
- "model.layers.46.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
969
- "model.layers.46.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
970
- "model.layers.46.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
971
- "model.layers.46.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
972
- "model.layers.46.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
973
- "model.layers.46.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
974
- "model.layers.46.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
975
- "model.layers.46.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
976
- "model.layers.46.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
977
- "model.layers.46.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
978
- "model.layers.47.input_layernorm.weight": "model-00002-of-00002.safetensors",
979
- "model.layers.47.mlp.down_proj.biases": "model-00002-of-00002.safetensors",
980
- "model.layers.47.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
981
- "model.layers.47.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
982
- "model.layers.47.mlp.gate_proj.biases": "model-00002-of-00002.safetensors",
983
- "model.layers.47.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
984
- "model.layers.47.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
985
- "model.layers.47.mlp.up_proj.biases": "model-00002-of-00002.safetensors",
986
- "model.layers.47.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
987
- "model.layers.47.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
988
- "model.layers.47.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
989
- "model.layers.47.self_attn.k_proj.biases": "model-00002-of-00002.safetensors",
990
- "model.layers.47.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
991
- "model.layers.47.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
992
- "model.layers.47.self_attn.o_proj.biases": "model-00002-of-00002.safetensors",
993
- "model.layers.47.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
994
- "model.layers.47.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
995
- "model.layers.47.self_attn.q_proj.biases": "model-00002-of-00002.safetensors",
996
- "model.layers.47.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
997
- "model.layers.47.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
998
- "model.layers.47.self_attn.v_proj.biases": "model-00002-of-00002.safetensors",
999
- "model.layers.47.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
1000
- "model.layers.47.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
1001
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
1002
- "model.layers.5.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
1003
- "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1004
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
1005
- "model.layers.5.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
1006
- "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1007
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
1008
- "model.layers.5.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
1009
- "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1010
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
1011
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1012
- "model.layers.5.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
1013
- "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1014
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
1015
- "model.layers.5.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
1016
- "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1017
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
1018
- "model.layers.5.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
1019
- "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1020
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
1021
- "model.layers.5.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
1022
- "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1023
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
1024
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
1025
- "model.layers.6.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
1026
- "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1027
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
1028
- "model.layers.6.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
1029
- "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1030
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
1031
- "model.layers.6.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
1032
- "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1033
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
1034
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1035
- "model.layers.6.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
1036
- "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1037
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
1038
- "model.layers.6.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
1039
- "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1040
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
1041
- "model.layers.6.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
1042
- "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1043
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
1044
- "model.layers.6.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
1045
- "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1046
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
1047
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
1048
- "model.layers.7.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
1049
- "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1050
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
1051
- "model.layers.7.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
1052
- "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1053
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
1054
- "model.layers.7.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
1055
- "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1056
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
1057
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1058
- "model.layers.7.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
1059
- "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1060
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
1061
- "model.layers.7.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
1062
- "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1063
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
1064
- "model.layers.7.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
1065
- "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1066
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
1067
- "model.layers.7.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
1068
- "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1069
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
1070
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
1071
- "model.layers.8.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
1072
- "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1073
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
1074
- "model.layers.8.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
1075
- "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1076
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
1077
- "model.layers.8.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
1078
- "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1079
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
1080
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1081
- "model.layers.8.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
1082
- "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1083
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
1084
- "model.layers.8.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
1085
- "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1086
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
1087
- "model.layers.8.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
1088
- "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1089
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
1090
- "model.layers.8.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
1091
- "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1092
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
1093
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
1094
- "model.layers.9.mlp.down_proj.biases": "model-00001-of-00002.safetensors",
1095
- "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
1096
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
1097
- "model.layers.9.mlp.gate_proj.biases": "model-00001-of-00002.safetensors",
1098
- "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
1099
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
1100
- "model.layers.9.mlp.up_proj.biases": "model-00001-of-00002.safetensors",
1101
- "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
1102
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
1103
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
1104
- "model.layers.9.self_attn.k_proj.biases": "model-00001-of-00002.safetensors",
1105
- "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
1106
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
1107
- "model.layers.9.self_attn.o_proj.biases": "model-00001-of-00002.safetensors",
1108
- "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
1109
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
1110
- "model.layers.9.self_attn.q_proj.biases": "model-00001-of-00002.safetensors",
1111
- "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
1112
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
1113
- "model.layers.9.self_attn.v_proj.biases": "model-00001-of-00002.safetensors",
1114
- "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
1115
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
1116
- "model.norm.weight": "model-00002-of-00002.safetensors"
1117
- }
1118
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
special_tokens_map.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|im_start|>"
4
- ],
5
- "bos_token": {
6
- "content": "<|startoftext|>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "eos_token": {
13
- "content": "<|im_end|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false
18
- },
19
- "pad_token": {
20
- "content": "<unk>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false
25
- },
26
- "unk_token": {
27
- "content": "<unk>",
28
- "lstrip": false,
29
- "normalized": false,
30
- "rstrip": false,
31
- "single_word": false
32
- }
33
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
- size 1033105
 
 
 
 
tokenizer_config.json DELETED
@@ -1,61 +0,0 @@
1
- {
2
- "add_bos_token": false,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<|startoftext|>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "<|endoftext|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- },
29
- "6": {
30
- "content": "<|im_start|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "7": {
38
- "content": "<|im_end|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
- }
45
- },
46
- "additional_special_tokens": [
47
- "<|im_start|>"
48
- ],
49
- "bos_token": "<|startoftext|>",
50
- "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
51
- "clean_up_tokenization_spaces": false,
52
- "eos_token": "<|im_end|>",
53
- "model_max_length": 4096,
54
- "pad_token": "<unk>",
55
- "padding_side": "left",
56
- "sp_model_kwargs": {},
57
- "split_special_tokens": false,
58
- "tokenizer_class": "LlamaTokenizer",
59
- "unk_token": "<unk>",
60
- "use_default_system_prompt": false
61
- }