Model save
Browse files- README.md +529 -0
- generation_config.json +6 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +280 -0
README.md
ADDED
@@ -0,0 +1,529 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
base_model: deepseek-ai/deepseek-math-7b-base
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: albert-no-variable-items-length
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# albert-no-variable-items-length
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.0201
|
21 |
+
|
22 |
+
## Model description
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training and evaluation data
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Training procedure
|
35 |
+
|
36 |
+
### Training hyperparameters
|
37 |
+
|
38 |
+
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 3e-06
|
40 |
+
- train_batch_size: 16
|
41 |
+
- eval_batch_size: 8
|
42 |
+
- seed: 42
|
43 |
+
- gradient_accumulation_steps: 4
|
44 |
+
- total_train_batch_size: 64
|
45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
+
- lr_scheduler_type: constant_with_warmup
|
47 |
+
- lr_scheduler_warmup_steps: 1
|
48 |
+
- num_epochs: 3
|
49 |
+
|
50 |
+
### Training results
|
51 |
+
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 0.7887 | 0.01 | 1 | 0.3267 |
|
55 |
+
| 0.8195 | 0.01 | 2 | 0.3220 |
|
56 |
+
| 0.7704 | 0.02 | 3 | 0.3179 |
|
57 |
+
| 0.7745 | 0.03 | 4 | 0.3148 |
|
58 |
+
| 0.7651 | 0.03 | 5 | 0.3115 |
|
59 |
+
| 0.7484 | 0.04 | 6 | 0.3085 |
|
60 |
+
| 0.7621 | 0.04 | 7 | 0.3065 |
|
61 |
+
| 0.7409 | 0.05 | 8 | 0.3033 |
|
62 |
+
| 0.7138 | 0.06 | 9 | 0.3003 |
|
63 |
+
| 0.7204 | 0.06 | 10 | 0.2985 |
|
64 |
+
| 0.6912 | 0.07 | 11 | 0.2952 |
|
65 |
+
| 0.7163 | 0.08 | 12 | 0.2922 |
|
66 |
+
| 0.6911 | 0.08 | 13 | 0.2901 |
|
67 |
+
| 0.6774 | 0.09 | 14 | 0.2878 |
|
68 |
+
| 0.6692 | 0.1 | 15 | 0.2851 |
|
69 |
+
| 0.6055 | 0.1 | 16 | 0.2825 |
|
70 |
+
| 0.4833 | 0.11 | 17 | 0.2801 |
|
71 |
+
| 0.4824 | 0.12 | 18 | 0.2765 |
|
72 |
+
| 0.4753 | 0.12 | 19 | 0.2752 |
|
73 |
+
| 0.4653 | 0.13 | 20 | 0.2722 |
|
74 |
+
| 0.466 | 0.13 | 21 | 0.2696 |
|
75 |
+
| 0.4599 | 0.14 | 22 | 0.2685 |
|
76 |
+
| 0.4484 | 0.15 | 23 | 0.2647 |
|
77 |
+
| 0.4508 | 0.15 | 24 | 0.2615 |
|
78 |
+
| 0.4436 | 0.16 | 25 | 0.2594 |
|
79 |
+
| 0.4526 | 0.17 | 26 | 0.2565 |
|
80 |
+
| 0.4332 | 0.17 | 27 | 0.2551 |
|
81 |
+
| 0.4246 | 0.18 | 28 | 0.2515 |
|
82 |
+
| 0.4241 | 0.19 | 29 | 0.2480 |
|
83 |
+
| 0.4173 | 0.19 | 30 | 0.2453 |
|
84 |
+
| 0.4031 | 0.2 | 31 | 0.2435 |
|
85 |
+
| 0.4122 | 0.2 | 32 | 0.2400 |
|
86 |
+
| 0.408 | 0.21 | 33 | 0.2386 |
|
87 |
+
| 0.3971 | 0.22 | 34 | 0.2361 |
|
88 |
+
| 0.4002 | 0.22 | 35 | 0.2337 |
|
89 |
+
| 0.3881 | 0.23 | 36 | 0.2310 |
|
90 |
+
| 0.3965 | 0.24 | 37 | 0.2272 |
|
91 |
+
| 0.3731 | 0.24 | 38 | 0.2245 |
|
92 |
+
| 0.3743 | 0.25 | 39 | 0.2211 |
|
93 |
+
| 0.3625 | 0.26 | 40 | 0.2191 |
|
94 |
+
| 0.3619 | 0.26 | 41 | 0.2167 |
|
95 |
+
| 0.3557 | 0.27 | 42 | 0.2149 |
|
96 |
+
| 0.3539 | 0.28 | 43 | 0.2107 |
|
97 |
+
| 0.3367 | 0.28 | 44 | 0.2089 |
|
98 |
+
| 0.3427 | 0.29 | 45 | 0.2061 |
|
99 |
+
| 0.333 | 0.29 | 46 | 0.2026 |
|
100 |
+
| 0.308 | 0.3 | 47 | 0.1996 |
|
101 |
+
| 0.2572 | 0.31 | 48 | 0.1969 |
|
102 |
+
| 0.2568 | 0.31 | 49 | 0.1934 |
|
103 |
+
| 0.2452 | 0.32 | 50 | 0.1915 |
|
104 |
+
| 0.2406 | 0.33 | 51 | 0.1874 |
|
105 |
+
| 0.2395 | 0.33 | 52 | 0.1834 |
|
106 |
+
| 0.2337 | 0.34 | 53 | 0.1805 |
|
107 |
+
| 0.2223 | 0.35 | 54 | 0.1767 |
|
108 |
+
| 0.2295 | 0.35 | 55 | 0.1732 |
|
109 |
+
| 0.222 | 0.36 | 56 | 0.1692 |
|
110 |
+
| 0.2174 | 0.36 | 57 | 0.1653 |
|
111 |
+
| 0.2064 | 0.37 | 58 | 0.1637 |
|
112 |
+
| 0.2075 | 0.38 | 59 | 0.1591 |
|
113 |
+
| 0.2014 | 0.38 | 60 | 0.1559 |
|
114 |
+
| 0.1963 | 0.39 | 61 | 0.1519 |
|
115 |
+
| 0.1908 | 0.4 | 62 | 0.1485 |
|
116 |
+
| 0.1963 | 0.4 | 63 | 0.1445 |
|
117 |
+
| 0.1793 | 0.41 | 64 | 0.1408 |
|
118 |
+
| 0.179 | 0.42 | 65 | 0.1377 |
|
119 |
+
| 0.1645 | 0.42 | 66 | 0.1334 |
|
120 |
+
| 0.1651 | 0.43 | 67 | 0.1299 |
|
121 |
+
| 0.1632 | 0.44 | 68 | 0.1264 |
|
122 |
+
| 0.1549 | 0.44 | 69 | 0.1224 |
|
123 |
+
| 0.1479 | 0.45 | 70 | 0.1186 |
|
124 |
+
| 0.1491 | 0.45 | 71 | 0.1153 |
|
125 |
+
| 0.1397 | 0.46 | 72 | 0.1109 |
|
126 |
+
| 0.1384 | 0.47 | 73 | 0.1069 |
|
127 |
+
| 0.1308 | 0.47 | 74 | 0.1025 |
|
128 |
+
| 0.1144 | 0.48 | 75 | 0.0987 |
|
129 |
+
| 0.1191 | 0.49 | 76 | 0.0946 |
|
130 |
+
| 0.1132 | 0.49 | 77 | 0.0910 |
|
131 |
+
| 0.1057 | 0.5 | 78 | 0.0867 |
|
132 |
+
| 0.0911 | 0.51 | 79 | 0.0841 |
|
133 |
+
| 0.1005 | 0.51 | 80 | 0.0812 |
|
134 |
+
| 0.0885 | 0.52 | 81 | 0.0790 |
|
135 |
+
| 0.091 | 0.52 | 82 | 0.0766 |
|
136 |
+
| 0.0841 | 0.53 | 83 | 0.0742 |
|
137 |
+
| 0.0808 | 0.54 | 84 | 0.0728 |
|
138 |
+
| 0.0752 | 0.54 | 85 | 0.0708 |
|
139 |
+
| 0.0717 | 0.55 | 86 | 0.0690 |
|
140 |
+
| 0.0767 | 0.56 | 87 | 0.0676 |
|
141 |
+
| 0.069 | 0.56 | 88 | 0.0658 |
|
142 |
+
| 0.0721 | 0.57 | 89 | 0.0643 |
|
143 |
+
| 0.074 | 0.58 | 90 | 0.0635 |
|
144 |
+
| 0.0633 | 0.58 | 91 | 0.0621 |
|
145 |
+
| 0.0706 | 0.59 | 92 | 0.0609 |
|
146 |
+
| 0.0575 | 0.6 | 93 | 0.0587 |
|
147 |
+
| 0.0641 | 0.6 | 94 | 0.0584 |
|
148 |
+
| 0.0574 | 0.61 | 95 | 0.0572 |
|
149 |
+
| 0.0658 | 0.61 | 96 | 0.0567 |
|
150 |
+
| 0.0696 | 0.62 | 97 | 0.0553 |
|
151 |
+
| 0.0603 | 0.63 | 98 | 0.0544 |
|
152 |
+
| 0.0571 | 0.63 | 99 | 0.0537 |
|
153 |
+
| 0.057 | 0.64 | 100 | 0.0527 |
|
154 |
+
| 0.0569 | 0.65 | 101 | 0.0514 |
|
155 |
+
| 0.0521 | 0.65 | 102 | 0.0511 |
|
156 |
+
| 0.052 | 0.66 | 103 | 0.0501 |
|
157 |
+
| 0.0529 | 0.67 | 104 | 0.0490 |
|
158 |
+
| 0.0523 | 0.67 | 105 | 0.0490 |
|
159 |
+
| 0.0567 | 0.68 | 106 | 0.0480 |
|
160 |
+
| 0.0547 | 0.68 | 107 | 0.0475 |
|
161 |
+
| 0.0509 | 0.69 | 108 | 0.0468 |
|
162 |
+
| 0.0506 | 0.7 | 109 | 0.0462 |
|
163 |
+
| 0.0533 | 0.7 | 110 | 0.0458 |
|
164 |
+
| 0.0544 | 0.71 | 111 | 0.0449 |
|
165 |
+
| 0.0521 | 0.72 | 112 | 0.0442 |
|
166 |
+
| 0.0527 | 0.72 | 113 | 0.0439 |
|
167 |
+
| 0.0495 | 0.73 | 114 | 0.0436 |
|
168 |
+
| 0.0471 | 0.74 | 115 | 0.0430 |
|
169 |
+
| 0.0442 | 0.74 | 116 | 0.0424 |
|
170 |
+
| 0.0432 | 0.75 | 117 | 0.0421 |
|
171 |
+
| 0.0451 | 0.76 | 118 | 0.0420 |
|
172 |
+
| 0.0498 | 0.76 | 119 | 0.0409 |
|
173 |
+
| 0.0468 | 0.77 | 120 | 0.0409 |
|
174 |
+
| 0.0474 | 0.77 | 121 | 0.0403 |
|
175 |
+
| 0.0462 | 0.78 | 122 | 0.0399 |
|
176 |
+
| 0.037 | 0.79 | 123 | 0.0397 |
|
177 |
+
| 0.041 | 0.79 | 124 | 0.0393 |
|
178 |
+
| 0.045 | 0.8 | 125 | 0.0387 |
|
179 |
+
| 0.045 | 0.81 | 126 | 0.0393 |
|
180 |
+
| 0.0416 | 0.81 | 127 | 0.0381 |
|
181 |
+
| 0.0418 | 0.82 | 128 | 0.0383 |
|
182 |
+
| 0.0382 | 0.83 | 129 | 0.0377 |
|
183 |
+
| 0.0444 | 0.83 | 130 | 0.0376 |
|
184 |
+
| 0.0404 | 0.84 | 131 | 0.0373 |
|
185 |
+
| 0.0438 | 0.84 | 132 | 0.0369 |
|
186 |
+
| 0.0411 | 0.85 | 133 | 0.0365 |
|
187 |
+
| 0.041 | 0.86 | 134 | 0.0364 |
|
188 |
+
| 0.0425 | 0.86 | 135 | 0.0362 |
|
189 |
+
| 0.0418 | 0.87 | 136 | 0.0356 |
|
190 |
+
| 0.0407 | 0.88 | 137 | 0.0358 |
|
191 |
+
| 0.04 | 0.88 | 138 | 0.0362 |
|
192 |
+
| 0.0382 | 0.89 | 139 | 0.0358 |
|
193 |
+
| 0.0415 | 0.9 | 140 | 0.0351 |
|
194 |
+
| 0.0374 | 0.9 | 141 | 0.0353 |
|
195 |
+
| 0.0377 | 0.91 | 142 | 0.0350 |
|
196 |
+
| 0.0368 | 0.92 | 143 | 0.0348 |
|
197 |
+
| 0.0389 | 0.92 | 144 | 0.0348 |
|
198 |
+
| 0.035 | 0.93 | 145 | 0.0344 |
|
199 |
+
| 0.0377 | 0.93 | 146 | 0.0346 |
|
200 |
+
| 0.0394 | 0.94 | 147 | 0.0344 |
|
201 |
+
| 0.0349 | 0.95 | 148 | 0.0344 |
|
202 |
+
| 0.0379 | 0.95 | 149 | 0.0341 |
|
203 |
+
| 0.0336 | 0.96 | 150 | 0.0340 |
|
204 |
+
| 0.037 | 0.97 | 151 | 0.0338 |
|
205 |
+
| 0.0338 | 0.97 | 152 | 0.0337 |
|
206 |
+
| 0.0384 | 0.98 | 153 | 0.0337 |
|
207 |
+
| 0.0385 | 0.99 | 154 | 0.0333 |
|
208 |
+
| 0.0345 | 0.99 | 155 | 0.0333 |
|
209 |
+
| 0.0354 | 1.0 | 156 | 0.0330 |
|
210 |
+
| 0.0359 | 1.0 | 157 | 0.0324 |
|
211 |
+
| 0.0372 | 1.01 | 158 | 0.0328 |
|
212 |
+
| 0.0337 | 1.02 | 159 | 0.0321 |
|
213 |
+
| 0.0344 | 1.02 | 160 | 0.0322 |
|
214 |
+
| 0.0351 | 1.03 | 161 | 0.0319 |
|
215 |
+
| 0.0324 | 1.04 | 162 | 0.0324 |
|
216 |
+
| 0.034 | 1.04 | 163 | 0.0320 |
|
217 |
+
| 0.0287 | 1.05 | 164 | 0.0321 |
|
218 |
+
| 0.03 | 1.06 | 165 | 0.0320 |
|
219 |
+
| 0.0314 | 1.06 | 166 | 0.0319 |
|
220 |
+
| 0.0275 | 1.07 | 167 | 0.0315 |
|
221 |
+
| 0.0213 | 1.08 | 168 | 0.0321 |
|
222 |
+
| 0.0277 | 1.08 | 169 | 0.0321 |
|
223 |
+
| 0.0275 | 1.09 | 170 | 0.0319 |
|
224 |
+
| 0.0182 | 1.09 | 171 | 0.0320 |
|
225 |
+
| 0.0236 | 1.1 | 172 | 0.0319 |
|
226 |
+
| 0.0319 | 1.11 | 173 | 0.0312 |
|
227 |
+
| 0.0358 | 1.11 | 174 | 0.0319 |
|
228 |
+
| 0.0328 | 1.12 | 175 | 0.0319 |
|
229 |
+
| 0.0337 | 1.13 | 176 | 0.0318 |
|
230 |
+
| 0.0382 | 1.13 | 177 | 0.0319 |
|
231 |
+
| 0.0315 | 1.14 | 178 | 0.0312 |
|
232 |
+
| 0.0308 | 1.15 | 179 | 0.0320 |
|
233 |
+
| 0.0314 | 1.15 | 180 | 0.0325 |
|
234 |
+
| 0.0312 | 1.16 | 181 | 0.0324 |
|
235 |
+
| 0.0326 | 1.16 | 182 | 0.0327 |
|
236 |
+
| 0.0278 | 1.17 | 183 | 0.0332 |
|
237 |
+
| 0.0264 | 1.18 | 184 | 0.0329 |
|
238 |
+
| 0.0307 | 1.18 | 185 | 0.0334 |
|
239 |
+
| 0.0255 | 1.19 | 186 | 0.0336 |
|
240 |
+
| 0.0284 | 1.2 | 187 | 0.0338 |
|
241 |
+
| 0.029 | 1.2 | 188 | 0.0342 |
|
242 |
+
| 0.0299 | 1.21 | 189 | 0.0343 |
|
243 |
+
| 0.0317 | 1.22 | 190 | 0.0342 |
|
244 |
+
| 0.0319 | 1.22 | 191 | 0.0345 |
|
245 |
+
| 0.0281 | 1.23 | 192 | 0.0344 |
|
246 |
+
| 0.0293 | 1.24 | 193 | 0.0341 |
|
247 |
+
| 0.0256 | 1.24 | 194 | 0.0344 |
|
248 |
+
| 0.0253 | 1.25 | 195 | 0.0345 |
|
249 |
+
| 0.0255 | 1.25 | 196 | 0.0344 |
|
250 |
+
| 0.0238 | 1.26 | 197 | 0.0343 |
|
251 |
+
| 0.0247 | 1.27 | 198 | 0.0338 |
|
252 |
+
| 0.0239 | 1.27 | 199 | 0.0344 |
|
253 |
+
| 0.0248 | 1.28 | 200 | 0.0345 |
|
254 |
+
| 0.0253 | 1.29 | 201 | 0.0343 |
|
255 |
+
| 0.0252 | 1.29 | 202 | 0.0340 |
|
256 |
+
| 0.0275 | 1.3 | 203 | 0.0340 |
|
257 |
+
| 0.0376 | 1.31 | 204 | 0.0336 |
|
258 |
+
| 0.0374 | 1.31 | 205 | 0.0333 |
|
259 |
+
| 0.0397 | 1.32 | 206 | 0.0331 |
|
260 |
+
| 0.0361 | 1.32 | 207 | 0.0322 |
|
261 |
+
| 0.0402 | 1.33 | 208 | 0.0319 |
|
262 |
+
| 0.0307 | 1.34 | 209 | 0.0317 |
|
263 |
+
| 0.0305 | 1.34 | 210 | 0.0309 |
|
264 |
+
| 0.0285 | 1.35 | 211 | 0.0307 |
|
265 |
+
| 0.0301 | 1.36 | 212 | 0.0307 |
|
266 |
+
| 0.0298 | 1.36 | 213 | 0.0306 |
|
267 |
+
| 0.0278 | 1.37 | 214 | 0.0305 |
|
268 |
+
| 0.0283 | 1.38 | 215 | 0.0303 |
|
269 |
+
| 0.0311 | 1.38 | 216 | 0.0304 |
|
270 |
+
| 0.0314 | 1.39 | 217 | 0.0306 |
|
271 |
+
| 0.0301 | 1.4 | 218 | 0.0304 |
|
272 |
+
| 0.0301 | 1.4 | 219 | 0.0303 |
|
273 |
+
| 0.0297 | 1.41 | 220 | 0.0299 |
|
274 |
+
| 0.0298 | 1.41 | 221 | 0.0300 |
|
275 |
+
| 0.0316 | 1.42 | 222 | 0.0299 |
|
276 |
+
| 0.0258 | 1.43 | 223 | 0.0296 |
|
277 |
+
| 0.0297 | 1.43 | 224 | 0.0297 |
|
278 |
+
| 0.0307 | 1.44 | 225 | 0.0289 |
|
279 |
+
| 0.0256 | 1.45 | 226 | 0.0285 |
|
280 |
+
| 0.0291 | 1.45 | 227 | 0.0285 |
|
281 |
+
| 0.0295 | 1.46 | 228 | 0.0286 |
|
282 |
+
| 0.0263 | 1.47 | 229 | 0.0283 |
|
283 |
+
| 0.0301 | 1.47 | 230 | 0.0284 |
|
284 |
+
| 0.0289 | 1.48 | 231 | 0.0285 |
|
285 |
+
| 0.0272 | 1.48 | 232 | 0.0286 |
|
286 |
+
| 0.0297 | 1.49 | 233 | 0.0286 |
|
287 |
+
| 0.0261 | 1.5 | 234 | 0.0286 |
|
288 |
+
| 0.0254 | 1.5 | 235 | 0.0286 |
|
289 |
+
| 0.0298 | 1.51 | 236 | 0.0284 |
|
290 |
+
| 0.0329 | 1.52 | 237 | 0.0278 |
|
291 |
+
| 0.0325 | 1.52 | 238 | 0.0281 |
|
292 |
+
| 0.0297 | 1.53 | 239 | 0.0280 |
|
293 |
+
| 0.0274 | 1.54 | 240 | 0.0281 |
|
294 |
+
| 0.0291 | 1.54 | 241 | 0.0277 |
|
295 |
+
| 0.0271 | 1.55 | 242 | 0.0279 |
|
296 |
+
| 0.0283 | 1.56 | 243 | 0.0278 |
|
297 |
+
| 0.0258 | 1.56 | 244 | 0.0277 |
|
298 |
+
| 0.0271 | 1.57 | 245 | 0.0276 |
|
299 |
+
| 0.0279 | 1.57 | 246 | 0.0273 |
|
300 |
+
| 0.0282 | 1.58 | 247 | 0.0274 |
|
301 |
+
| 0.0286 | 1.59 | 248 | 0.0272 |
|
302 |
+
| 0.0248 | 1.59 | 249 | 0.0268 |
|
303 |
+
| 0.0268 | 1.6 | 250 | 0.0272 |
|
304 |
+
| 0.0239 | 1.61 | 251 | 0.0271 |
|
305 |
+
| 0.0321 | 1.61 | 252 | 0.0268 |
|
306 |
+
| 0.0305 | 1.62 | 253 | 0.0266 |
|
307 |
+
| 0.0307 | 1.63 | 254 | 0.0263 |
|
308 |
+
| 0.0245 | 1.63 | 255 | 0.0266 |
|
309 |
+
| 0.0261 | 1.64 | 256 | 0.0268 |
|
310 |
+
| 0.0264 | 1.64 | 257 | 0.0262 |
|
311 |
+
| 0.0268 | 1.65 | 258 | 0.0264 |
|
312 |
+
| 0.0253 | 1.66 | 259 | 0.0261 |
|
313 |
+
| 0.0267 | 1.66 | 260 | 0.0261 |
|
314 |
+
| 0.0276 | 1.67 | 261 | 0.0262 |
|
315 |
+
| 0.0269 | 1.68 | 262 | 0.0260 |
|
316 |
+
| 0.0265 | 1.68 | 263 | 0.0262 |
|
317 |
+
| 0.0267 | 1.69 | 264 | 0.0262 |
|
318 |
+
| 0.0256 | 1.7 | 265 | 0.0260 |
|
319 |
+
| 0.0285 | 1.7 | 266 | 0.0257 |
|
320 |
+
| 0.0305 | 1.71 | 267 | 0.0259 |
|
321 |
+
| 0.0302 | 1.72 | 268 | 0.0262 |
|
322 |
+
| 0.0294 | 1.72 | 269 | 0.0258 |
|
323 |
+
| 0.0295 | 1.73 | 270 | 0.0255 |
|
324 |
+
| 0.027 | 1.73 | 271 | 0.0255 |
|
325 |
+
| 0.0276 | 1.74 | 272 | 0.0256 |
|
326 |
+
| 0.0256 | 1.75 | 273 | 0.0257 |
|
327 |
+
| 0.0248 | 1.75 | 274 | 0.0257 |
|
328 |
+
| 0.0305 | 1.76 | 275 | 0.0253 |
|
329 |
+
| 0.029 | 1.77 | 276 | 0.0253 |
|
330 |
+
| 0.0296 | 1.77 | 277 | 0.0251 |
|
331 |
+
| 0.0307 | 1.78 | 278 | 0.0250 |
|
332 |
+
| 0.0247 | 1.79 | 279 | 0.0250 |
|
333 |
+
| 0.0235 | 1.79 | 280 | 0.0250 |
|
334 |
+
| 0.0267 | 1.8 | 281 | 0.0250 |
|
335 |
+
| 0.0278 | 1.8 | 282 | 0.0246 |
|
336 |
+
| 0.0277 | 1.81 | 283 | 0.0248 |
|
337 |
+
| 0.0266 | 1.82 | 284 | 0.0242 |
|
338 |
+
| 0.0232 | 1.82 | 285 | 0.0244 |
|
339 |
+
| 0.0288 | 1.83 | 286 | 0.0243 |
|
340 |
+
| 0.0276 | 1.84 | 287 | 0.0243 |
|
341 |
+
| 0.0295 | 1.84 | 288 | 0.0241 |
|
342 |
+
| 0.0253 | 1.85 | 289 | 0.0240 |
|
343 |
+
| 0.0267 | 1.86 | 290 | 0.0244 |
|
344 |
+
| 0.0286 | 1.86 | 291 | 0.0242 |
|
345 |
+
| 0.0272 | 1.87 | 292 | 0.0237 |
|
346 |
+
| 0.0267 | 1.88 | 293 | 0.0240 |
|
347 |
+
| 0.0251 | 1.88 | 294 | 0.0243 |
|
348 |
+
| 0.0257 | 1.89 | 295 | 0.0239 |
|
349 |
+
| 0.0283 | 1.89 | 296 | 0.0237 |
|
350 |
+
| 0.0246 | 1.9 | 297 | 0.0238 |
|
351 |
+
| 0.0241 | 1.91 | 298 | 0.0238 |
|
352 |
+
| 0.0259 | 1.91 | 299 | 0.0241 |
|
353 |
+
| 0.0246 | 1.92 | 300 | 0.0237 |
|
354 |
+
| 0.0253 | 1.93 | 301 | 0.0239 |
|
355 |
+
| 0.0257 | 1.93 | 302 | 0.0237 |
|
356 |
+
| 0.0232 | 1.94 | 303 | 0.0238 |
|
357 |
+
| 0.0241 | 1.95 | 304 | 0.0237 |
|
358 |
+
| 0.0254 | 1.95 | 305 | 0.0237 |
|
359 |
+
| 0.0227 | 1.96 | 306 | 0.0238 |
|
360 |
+
| 0.023 | 1.96 | 307 | 0.0238 |
|
361 |
+
| 0.0232 | 1.97 | 308 | 0.0238 |
|
362 |
+
| 0.0268 | 1.98 | 309 | 0.0234 |
|
363 |
+
| 0.027 | 1.98 | 310 | 0.0237 |
|
364 |
+
| 0.0243 | 1.99 | 311 | 0.0235 |
|
365 |
+
| 0.025 | 2.0 | 312 | 0.0235 |
|
366 |
+
| 0.0185 | 2.0 | 313 | 0.0235 |
|
367 |
+
| 0.0153 | 2.01 | 314 | 0.0234 |
|
368 |
+
| 0.0119 | 2.02 | 315 | 0.0236 |
|
369 |
+
| 0.0094 | 2.02 | 316 | 0.0235 |
|
370 |
+
| 0.0171 | 2.03 | 317 | 0.0237 |
|
371 |
+
| 0.0121 | 2.04 | 318 | 0.0235 |
|
372 |
+
| 0.0135 | 2.04 | 319 | 0.0231 |
|
373 |
+
| 0.0182 | 2.05 | 320 | 0.0235 |
|
374 |
+
| 0.0128 | 2.05 | 321 | 0.0232 |
|
375 |
+
| 0.014 | 2.06 | 322 | 0.0235 |
|
376 |
+
| 0.0142 | 2.07 | 323 | 0.0237 |
|
377 |
+
| 0.0084 | 2.07 | 324 | 0.0236 |
|
378 |
+
| 0.0137 | 2.08 | 325 | 0.0235 |
|
379 |
+
| 0.0144 | 2.09 | 326 | 0.0238 |
|
380 |
+
| 0.0114 | 2.09 | 327 | 0.0237 |
|
381 |
+
| 0.0104 | 2.1 | 328 | 0.0239 |
|
382 |
+
| 0.0205 | 2.11 | 329 | 0.0234 |
|
383 |
+
| 0.0234 | 2.11 | 330 | 0.0233 |
|
384 |
+
| 0.0227 | 2.12 | 331 | 0.0237 |
|
385 |
+
| 0.0217 | 2.12 | 332 | 0.0235 |
|
386 |
+
| 0.025 | 2.13 | 333 | 0.0237 |
|
387 |
+
| 0.0208 | 2.14 | 334 | 0.0245 |
|
388 |
+
| 0.0192 | 2.14 | 335 | 0.0245 |
|
389 |
+
| 0.0195 | 2.15 | 336 | 0.0249 |
|
390 |
+
| 0.0203 | 2.16 | 337 | 0.0253 |
|
391 |
+
| 0.0234 | 2.16 | 338 | 0.0252 |
|
392 |
+
| 0.0176 | 2.17 | 339 | 0.0259 |
|
393 |
+
| 0.018 | 2.18 | 340 | 0.0260 |
|
394 |
+
| 0.0188 | 2.18 | 341 | 0.0265 |
|
395 |
+
| 0.0198 | 2.19 | 342 | 0.0262 |
|
396 |
+
| 0.0172 | 2.2 | 343 | 0.0268 |
|
397 |
+
| 0.0184 | 2.2 | 344 | 0.0271 |
|
398 |
+
| 0.0192 | 2.21 | 345 | 0.0273 |
|
399 |
+
| 0.0203 | 2.21 | 346 | 0.0277 |
|
400 |
+
| 0.0221 | 2.22 | 347 | 0.0283 |
|
401 |
+
| 0.0189 | 2.23 | 348 | 0.0282 |
|
402 |
+
| 0.0196 | 2.23 | 349 | 0.0289 |
|
403 |
+
| 0.0205 | 2.24 | 350 | 0.0288 |
|
404 |
+
| 0.0168 | 2.25 | 351 | 0.0291 |
|
405 |
+
| 0.0176 | 2.25 | 352 | 0.0294 |
|
406 |
+
| 0.0165 | 2.26 | 353 | 0.0295 |
|
407 |
+
| 0.0148 | 2.27 | 354 | 0.0301 |
|
408 |
+
| 0.0178 | 2.27 | 355 | 0.0296 |
|
409 |
+
| 0.0163 | 2.28 | 356 | 0.0301 |
|
410 |
+
| 0.0203 | 2.28 | 357 | 0.0303 |
|
411 |
+
| 0.0163 | 2.29 | 358 | 0.0301 |
|
412 |
+
| 0.0183 | 2.3 | 359 | 0.0301 |
|
413 |
+
| 0.0266 | 2.3 | 360 | 0.0299 |
|
414 |
+
| 0.0295 | 2.31 | 361 | 0.0295 |
|
415 |
+
| 0.0293 | 2.32 | 362 | 0.0291 |
|
416 |
+
| 0.0248 | 2.32 | 363 | 0.0281 |
|
417 |
+
| 0.0285 | 2.33 | 364 | 0.0273 |
|
418 |
+
| 0.0252 | 2.34 | 365 | 0.0262 |
|
419 |
+
| 0.0222 | 2.34 | 366 | 0.0257 |
|
420 |
+
| 0.0208 | 2.35 | 367 | 0.0245 |
|
421 |
+
| 0.0194 | 2.36 | 368 | 0.0239 |
|
422 |
+
| 0.0217 | 2.36 | 369 | 0.0238 |
|
423 |
+
| 0.0183 | 2.37 | 370 | 0.0237 |
|
424 |
+
| 0.0218 | 2.37 | 371 | 0.0238 |
|
425 |
+
| 0.0224 | 2.38 | 372 | 0.0233 |
|
426 |
+
| 0.023 | 2.39 | 373 | 0.0235 |
|
427 |
+
| 0.0205 | 2.39 | 374 | 0.0235 |
|
428 |
+
| 0.0215 | 2.4 | 375 | 0.0237 |
|
429 |
+
| 0.0189 | 2.41 | 376 | 0.0238 |
|
430 |
+
| 0.0233 | 2.41 | 377 | 0.0236 |
|
431 |
+
| 0.0225 | 2.42 | 378 | 0.0238 |
|
432 |
+
| 0.0196 | 2.43 | 379 | 0.0233 |
|
433 |
+
| 0.0224 | 2.43 | 380 | 0.0232 |
|
434 |
+
| 0.0214 | 2.44 | 381 | 0.0234 |
|
435 |
+
| 0.0187 | 2.44 | 382 | 0.0233 |
|
436 |
+
| 0.0199 | 2.45 | 383 | 0.0231 |
|
437 |
+
| 0.0227 | 2.46 | 384 | 0.0231 |
|
438 |
+
| 0.0199 | 2.46 | 385 | 0.0231 |
|
439 |
+
| 0.0248 | 2.47 | 386 | 0.0231 |
|
440 |
+
| 0.0196 | 2.48 | 387 | 0.0231 |
|
441 |
+
| 0.0214 | 2.48 | 388 | 0.0231 |
|
442 |
+
| 0.022 | 2.49 | 389 | 0.0230 |
|
443 |
+
| 0.0201 | 2.5 | 390 | 0.0232 |
|
444 |
+
| 0.0205 | 2.5 | 391 | 0.0233 |
|
445 |
+
| 0.0221 | 2.51 | 392 | 0.0231 |
|
446 |
+
| 0.0255 | 2.52 | 393 | 0.0233 |
|
447 |
+
| 0.0235 | 2.52 | 394 | 0.0232 |
|
448 |
+
| 0.0235 | 2.53 | 395 | 0.0231 |
|
449 |
+
| 0.0237 | 2.53 | 396 | 0.0232 |
|
450 |
+
| 0.0216 | 2.54 | 397 | 0.0236 |
|
451 |
+
| 0.0229 | 2.55 | 398 | 0.0232 |
|
452 |
+
| 0.0191 | 2.55 | 399 | 0.0231 |
|
453 |
+
| 0.0211 | 2.56 | 400 | 0.0231 |
|
454 |
+
| 0.02 | 2.57 | 401 | 0.0232 |
|
455 |
+
| 0.0217 | 2.57 | 402 | 0.0228 |
|
456 |
+
| 0.0228 | 2.58 | 403 | 0.0228 |
|
457 |
+
| 0.0222 | 2.59 | 404 | 0.0230 |
|
458 |
+
| 0.0197 | 2.59 | 405 | 0.0226 |
|
459 |
+
| 0.0195 | 2.6 | 406 | 0.0225 |
|
460 |
+
| 0.0208 | 2.6 | 407 | 0.0227 |
|
461 |
+
| 0.0238 | 2.61 | 408 | 0.0226 |
|
462 |
+
| 0.0247 | 2.62 | 409 | 0.0222 |
|
463 |
+
| 0.0229 | 2.62 | 410 | 0.0223 |
|
464 |
+
| 0.0208 | 2.63 | 411 | 0.0222 |
|
465 |
+
| 0.0197 | 2.64 | 412 | 0.0220 |
|
466 |
+
| 0.0215 | 2.64 | 413 | 0.0222 |
|
467 |
+
| 0.0216 | 2.65 | 414 | 0.0221 |
|
468 |
+
| 0.0194 | 2.66 | 415 | 0.0221 |
|
469 |
+
| 0.0223 | 2.66 | 416 | 0.0220 |
|
470 |
+
| 0.022 | 2.67 | 417 | 0.0220 |
|
471 |
+
| 0.0204 | 2.68 | 418 | 0.0218 |
|
472 |
+
| 0.0211 | 2.68 | 419 | 0.0219 |
|
473 |
+
| 0.0205 | 2.69 | 420 | 0.0218 |
|
474 |
+
| 0.021 | 2.69 | 421 | 0.0213 |
|
475 |
+
| 0.0206 | 2.7 | 422 | 0.0216 |
|
476 |
+
| 0.0261 | 2.71 | 423 | 0.0215 |
|
477 |
+
| 0.0234 | 2.71 | 424 | 0.0216 |
|
478 |
+
| 0.0246 | 2.72 | 425 | 0.0215 |
|
479 |
+
| 0.0242 | 2.73 | 426 | 0.0217 |
|
480 |
+
| 0.0204 | 2.73 | 427 | 0.0217 |
|
481 |
+
| 0.0214 | 2.74 | 428 | 0.0215 |
|
482 |
+
| 0.0235 | 2.75 | 429 | 0.0216 |
|
483 |
+
| 0.0196 | 2.75 | 430 | 0.0213 |
|
484 |
+
| 0.0223 | 2.76 | 431 | 0.0213 |
|
485 |
+
| 0.0239 | 2.76 | 432 | 0.0211 |
|
486 |
+
| 0.0224 | 2.77 | 433 | 0.0210 |
|
487 |
+
| 0.025 | 2.78 | 434 | 0.0210 |
|
488 |
+
| 0.0228 | 2.78 | 435 | 0.0210 |
|
489 |
+
| 0.0182 | 2.79 | 436 | 0.0207 |
|
490 |
+
| 0.0214 | 2.8 | 437 | 0.0208 |
|
491 |
+
| 0.022 | 2.8 | 438 | 0.0212 |
|
492 |
+
| 0.0233 | 2.81 | 439 | 0.0205 |
|
493 |
+
| 0.0209 | 2.82 | 440 | 0.0208 |
|
494 |
+
| 0.0194 | 2.82 | 441 | 0.0206 |
|
495 |
+
| 0.0215 | 2.83 | 442 | 0.0205 |
|
496 |
+
| 0.0242 | 2.84 | 443 | 0.0204 |
|
497 |
+
| 0.0219 | 2.84 | 444 | 0.0205 |
|
498 |
+
| 0.0217 | 2.85 | 445 | 0.0205 |
|
499 |
+
| 0.0237 | 2.85 | 446 | 0.0205 |
|
500 |
+
| 0.0214 | 2.86 | 447 | 0.0205 |
|
501 |
+
| 0.0224 | 2.87 | 448 | 0.0201 |
|
502 |
+
| 0.0199 | 2.87 | 449 | 0.0206 |
|
503 |
+
| 0.0219 | 2.88 | 450 | 0.0202 |
|
504 |
+
| 0.022 | 2.89 | 451 | 0.0202 |
|
505 |
+
| 0.0224 | 2.89 | 452 | 0.0204 |
|
506 |
+
| 0.0214 | 2.9 | 453 | 0.0200 |
|
507 |
+
| 0.0185 | 2.91 | 454 | 0.0201 |
|
508 |
+
| 0.0219 | 2.91 | 455 | 0.0202 |
|
509 |
+
| 0.0204 | 2.92 | 456 | 0.0203 |
|
510 |
+
| 0.0198 | 2.92 | 457 | 0.0201 |
|
511 |
+
| 0.0214 | 2.93 | 458 | 0.0202 |
|
512 |
+
| 0.0184 | 2.94 | 459 | 0.0203 |
|
513 |
+
| 0.0191 | 2.94 | 460 | 0.0200 |
|
514 |
+
| 0.0221 | 2.95 | 461 | 0.0205 |
|
515 |
+
| 0.0192 | 2.96 | 462 | 0.0204 |
|
516 |
+
| 0.0186 | 2.96 | 463 | 0.0204 |
|
517 |
+
| 0.0176 | 2.97 | 464 | 0.0201 |
|
518 |
+
| 0.0209 | 2.98 | 465 | 0.0203 |
|
519 |
+
| 0.0233 | 2.98 | 466 | 0.0200 |
|
520 |
+
| 0.0189 | 2.99 | 467 | 0.0204 |
|
521 |
+
| 0.0214 | 3.0 | 468 | 0.0201 |
|
522 |
+
|
523 |
+
|
524 |
+
### Framework versions
|
525 |
+
|
526 |
+
- Transformers 4.37.2
|
527 |
+
- Pytorch 2.1.0a0+32f93b1
|
528 |
+
- Datasets 2.17.1
|
529 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 100000,
|
4 |
+
"eos_token_id": 100001,
|
5 |
+
"transformers_version": "4.37.2"
|
6 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c6eb832131b147ade2a43c58c7699af6997a9300458434a6a8f0e7835ec7d58
|
3 |
+
size 4987202208
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d11e3bd7bb39274628f4f1364142e7912fa83611e7a49c2be59395bd9c6fcb72
|
3 |
+
size 4980945440
|
model-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47f3ddac35c237d477480843a4af18a9eabf39473f6efc5a4df0c729ed8aa645
|
3 |
+
size 3852615520
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,280 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 13820731392
|
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-00002-of-00003.safetensors",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-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-00002-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-00002-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.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
225 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
226 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
227 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
228 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
229 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
230 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
231 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
232 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
233 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
234 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
235 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
236 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
237 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
238 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
239 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
240 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
241 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
242 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
243 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
244 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
245 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
246 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
247 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
248 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
249 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
250 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
251 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
252 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
253 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
254 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
255 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
256 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
257 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
258 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
259 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
260 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
261 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
262 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
263 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
264 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
265 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
266 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
267 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
268 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
269 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
270 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
271 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
272 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
273 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
274 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
275 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
276 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
277 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
278 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
279 |
+
}
|
280 |
+
}
|