Hugging Face's logo

thrunlab
/
Mistral_Sparse_refined_web_relu_2024-03-01

Text Generation
Transformers
Safetensors
sparse_mistral
Generated from Trainer
custom_code
Model card Files Community
vxbrandon commited on
Commit
7c06d71
•
1 Parent(s): 56fd322

End of training

Browse files
Files changed (5) hide show
  1. README.md +91 -0
  2. model-00001-of-00003.safetensors +2 -2
  3. model-00002-of-00003.safetensors +2 -2
  4. model-00003-of-00003.safetensors +2 -2
  5. model.safetensors.index.json +291 -291
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: mistralai/Mistral-7B-v0.1
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: Mistral_Sparse_refined_web_relu_2024-03-01
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # Mistral_Sparse_refined_web_relu_2024-03-01
15
+
16
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.5022
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 1e-05
38
+ - train_batch_size: 1
39
+ - eval_batch_size: 1
40
+ - seed: 0
41
+ - distributed_type: multi-GPU
42
+ - num_devices: 4
43
+ - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 16
45
+ - total_eval_batch_size: 4
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - training_steps: 750
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 8.7893 | 0.0 | 25 | 8.7124 |
55
+ | 8.1852 | 0.01 | 50 | 8.1766 |
56
+ | 7.7552 | 0.01 | 75 | 7.8055 |
57
+ | 7.5347 | 0.02 | 100 | 7.6044 |
58
+ | 7.1789 | 0.02 | 125 | 7.1167 |
59
+ | 4.7625 | 0.02 | 150 | 4.7156 |
60
+ | 3.7491 | 0.03 | 175 | 3.8005 |
61
+ | 3.2565 | 0.03 | 200 | 3.4172 |
62
+ | 3.0841 | 0.04 | 225 | 3.2310 |
63
+ | 2.9901 | 0.04 | 250 | 3.1131 |
64
+ | 2.8534 | 0.04 | 275 | 3.0370 |
65
+ | 2.8256 | 0.05 | 300 | 2.9857 |
66
+ | 2.792 | 0.05 | 325 | 2.9492 |
67
+ | 2.6055 | 0.06 | 350 | 2.9145 |
68
+ | 2.7474 | 0.06 | 375 | 2.8922 |
69
+ | 2.7788 | 0.06 | 400 | 2.8716 |
70
+ | 2.731 | 0.07 | 425 | 2.8528 |
71
+ | 2.6973 | 0.07 | 450 | 2.8403 |
72
+ | 2.5808 | 0.08 | 475 | 2.8249 |
73
+ | 2.6415 | 0.08 | 500 | 2.8154 |
74
+ | 2.718 | 0.08 | 525 | 2.8072 |
75
+ | 2.6225 | 0.09 | 550 | 2.7972 |
76
+ | 2.7265 | 0.09 | 575 | 2.7863 |
77
+ | 2.5424 | 0.1 | 600 | 2.7803 |
78
+ | 2.6148 | 0.1 | 625 | 2.7762 |
79
+ | 2.6546 | 0.1 | 650 | 2.7655 |
80
+ | 2.6728 | 0.11 | 675 | 2.7575 |
81
+ | 2.6039 | 0.11 | 700 | 2.7507 |
82
+ | 2.6226 | 0.12 | 725 | 2.7488 |
83
+ | 2.5294 | 0.12 | 750 | 2.7449 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.36.2
89
+ - Pytorch 2.1.2+cu121
90
+ - Datasets 2.15.0
91
+ - Tokenizers 0.15.0
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ee50aaf65a6517c6c27ea9abf221100a0c121908d2e2d802ea1abb2553c158d
3
- size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:919e0d1e0e7ebf172d8a31bb799de2c623ee6fcff82a5fc363d0d8cc017b14ca
3
+ size 4943163992
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a3428bed52cace24a592e853fac582d068d9c5b7fbbe4559e85b01c3d928e17
3
- size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d54f2d02dbd88f2a0dd3ad32af3701bbfbebac5b04d21c9a4f1cd803011e9f32
3
+ size 4999821144
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e8e5baabc4e695d67712962fb26b95559f4b2f6d8dba40bc75cfbd872ac57b3
3
- size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978926bb417f507ce3be91a5f2323cdadc2145368f11303f653c8ba4d7299ce1
3
+ size 4540517840
model.safetensors.index.json CHANGED
@@ -3,296 +3,296 @@
3
  "total_size": 14483464192
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "model-00003-of-00003.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
- "model.norm.weight": "model-00003-of-00003.safetensors"
297
  }
298
  }
 
3
  "total_size": 14483464192
4
  },
5
  "weight_map": {
6
+ "base_model.model.lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "base_model.model.model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "base_model.model.model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "base_model.model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "base_model.model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "base_model.model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "base_model.model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "base_model.model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "base_model.model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "base_model.model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "base_model.model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "base_model.model.model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "base_model.model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "base_model.model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "base_model.model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "base_model.model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "base_model.model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "base_model.model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "base_model.model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "base_model.model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "base_model.model.model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
27
+ "base_model.model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
28
+ "base_model.model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "base_model.model.model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "base_model.model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
31
+ "base_model.model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "base_model.model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "base_model.model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "base_model.model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "base_model.model.model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
+ "base_model.model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
+ "base_model.model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
38
+ "base_model.model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
+ "base_model.model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
+ "base_model.model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
41
+ "base_model.model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
42
+ "base_model.model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
43
+ "base_model.model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
44
+ "base_model.model.model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "base_model.model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "base_model.model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
+ "base_model.model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
+ "base_model.model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "base_model.model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
+ "base_model.model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
+ "base_model.model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
+ "base_model.model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
+ "base_model.model.model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "base_model.model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "base_model.model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "base_model.model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "base_model.model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "base_model.model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "base_model.model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "base_model.model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "base_model.model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "base_model.model.model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "base_model.model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "base_model.model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "base_model.model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "base_model.model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "base_model.model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "base_model.model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "base_model.model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "base_model.model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "base_model.model.model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "base_model.model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "base_model.model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "base_model.model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "base_model.model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "base_model.model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "base_model.model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "base_model.model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "base_model.model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "base_model.model.model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "base_model.model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "base_model.model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "base_model.model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "base_model.model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "base_model.model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "base_model.model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "base_model.model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "base_model.model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "base_model.model.model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "base_model.model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "base_model.model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "base_model.model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "base_model.model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "base_model.model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "base_model.model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "base_model.model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "base_model.model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "base_model.model.model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "base_model.model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "base_model.model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "base_model.model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "base_model.model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "base_model.model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "base_model.model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "base_model.model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "base_model.model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "base_model.model.model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "base_model.model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "base_model.model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "base_model.model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "base_model.model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "base_model.model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "base_model.model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "base_model.model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "base_model.model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "base_model.model.model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "base_model.model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "base_model.model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "base_model.model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "base_model.model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "base_model.model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "base_model.model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "base_model.model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "base_model.model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "base_model.model.model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "base_model.model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "base_model.model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "base_model.model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "base_model.model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "base_model.model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "base_model.model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "base_model.model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "base_model.model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "base_model.model.model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "base_model.model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "base_model.model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "base_model.model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "base_model.model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "base_model.model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "base_model.model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "base_model.model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "base_model.model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "base_model.model.model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
144
+ "base_model.model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
145
+ "base_model.model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
146
+ "base_model.model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
147
+ "base_model.model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
148
+ "base_model.model.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "base_model.model.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "base_model.model.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "base_model.model.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "base_model.model.model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
+ "base_model.model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
+ "base_model.model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
155
+ "base_model.model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
156
+ "base_model.model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
+ "base_model.model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
158
+ "base_model.model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
159
+ "base_model.model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
160
+ "base_model.model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
161
+ "base_model.model.model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
+ "base_model.model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
+ "base_model.model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
+ "base_model.model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
+ "base_model.model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
+ "base_model.model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
+ "base_model.model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
+ "base_model.model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
+ "base_model.model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
+ "base_model.model.model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
+ "base_model.model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
+ "base_model.model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
+ "base_model.model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
+ "base_model.model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
+ "base_model.model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
+ "base_model.model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
+ "base_model.model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
+ "base_model.model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
+ "base_model.model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
+ "base_model.model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
+ "base_model.model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
+ "base_model.model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
+ "base_model.model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
+ "base_model.model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
+ "base_model.model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
+ "base_model.model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
+ "base_model.model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
+ "base_model.model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "base_model.model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "base_model.model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "base_model.model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "base_model.model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "base_model.model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
+ "base_model.model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "base_model.model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
+ "base_model.model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
+ "base_model.model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "base_model.model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "base_model.model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "base_model.model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "base_model.model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "base_model.model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "base_model.model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "base_model.model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "base_model.model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "base_model.model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "base_model.model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "base_model.model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "base_model.model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "base_model.model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "base_model.model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "base_model.model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "base_model.model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "base_model.model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "base_model.model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "base_model.model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "base_model.model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "base_model.model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "base_model.model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "base_model.model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "base_model.model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "base_model.model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "base_model.model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "base_model.model.model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "base_model.model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "base_model.model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "base_model.model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "base_model.model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "base_model.model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "base_model.model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "base_model.model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "base_model.model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "base_model.model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "base_model.model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "base_model.model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "base_model.model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "base_model.model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "base_model.model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "base_model.model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "base_model.model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "base_model.model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "base_model.model.model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "base_model.model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "base_model.model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "base_model.model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "base_model.model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "base_model.model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "base_model.model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "base_model.model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "base_model.model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "base_model.model.model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "base_model.model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "base_model.model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "base_model.model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "base_model.model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "base_model.model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "base_model.model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "base_model.model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "base_model.model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "base_model.model.model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "base_model.model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "base_model.model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "base_model.model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "base_model.model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "base_model.model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "base_model.model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "base_model.model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "base_model.model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "base_model.model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "base_model.model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "base_model.model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "base_model.model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "base_model.model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "base_model.model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "base_model.model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "base_model.model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "base_model.model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "base_model.model.model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "base_model.model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "base_model.model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "base_model.model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "base_model.model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "base_model.model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "base_model.model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "base_model.model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "base_model.model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "base_model.model.model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "base_model.model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "base_model.model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "base_model.model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "base_model.model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "base_model.model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "base_model.model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "base_model.model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "base_model.model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "base_model.model.model.norm.weight": "model-00003-of-00003.safetensors"
297
  }
298
  }