Initial commit
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- logs.txt +196 -0
- mlc-chat-config.json +74 -0
- ndarray-cache.json +1913 -0
- params_shard_0.bin +3 -0
- params_shard_1.bin +3 -0
- params_shard_10.bin +3 -0
- params_shard_11.bin +3 -0
- params_shard_12.bin +3 -0
- params_shard_13.bin +3 -0
- params_shard_14.bin +3 -0
- params_shard_15.bin +3 -0
- params_shard_16.bin +3 -0
- params_shard_17.bin +3 -0
- params_shard_18.bin +3 -0
- params_shard_19.bin +3 -0
- params_shard_2.bin +3 -0
- params_shard_20.bin +3 -0
- params_shard_21.bin +3 -0
- params_shard_22.bin +3 -0
- params_shard_23.bin +3 -0
- params_shard_24.bin +3 -0
- params_shard_25.bin +3 -0
- params_shard_26.bin +3 -0
- params_shard_27.bin +3 -0
- params_shard_28.bin +3 -0
- params_shard_29.bin +3 -0
- params_shard_3.bin +3 -0
- params_shard_30.bin +3 -0
- params_shard_31.bin +3 -0
- params_shard_32.bin +3 -0
- params_shard_33.bin +3 -0
- params_shard_34.bin +3 -0
- params_shard_35.bin +3 -0
- params_shard_36.bin +3 -0
- params_shard_37.bin +3 -0
- params_shard_38.bin +3 -0
- params_shard_39.bin +3 -0
- params_shard_4.bin +3 -0
- params_shard_40.bin +3 -0
- params_shard_41.bin +3 -0
- params_shard_42.bin +3 -0
- params_shard_43.bin +3 -0
- params_shard_44.bin +3 -0
- params_shard_45.bin +3 -0
- params_shard_46.bin +3 -0
- params_shard_47.bin +3 -0
- params_shard_48.bin +3 -0
- params_shard_49.bin +3 -0
- params_shard_5.bin +3 -0
- params_shard_50.bin +3 -0
logs.txt
ADDED
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
0 |
0%| | 0/135 [00:00<?, ?it/s]
|
1 |
|
|
|
2 |
0%| | 0/135 [00:00<?, ?it/s]
|
3 |
|
|
|
4 |
0%| | 0/135 [00:03<?, ?it/s]
|
5 |
1%| | 1/135 [00:04<09:19, 4.17s/it]
|
6 |
|
|
|
7 |
1%| | 1/135 [00:04<09:19, 4.17s/it]
|
8 |
1%|▏ | 2/135 [00:04<04:37, 2.09s/it]
|
9 |
|
|
|
10 |
1%|▏ | 2/135 [00:04<04:37, 2.09s/it]
|
11 |
|
|
|
12 |
1%|▏ | 2/135 [00:04<04:37, 2.09s/it]
|
13 |
|
|
|
14 |
1%|▏ | 2/135 [00:04<04:37, 2.09s/it]
|
15 |
4%|▎ | 5/135 [00:05<01:27, 1.48it/s]
|
16 |
|
|
|
17 |
4%|▎ | 5/135 [00:05<01:27, 1.48it/s]
|
18 |
|
|
|
19 |
4%|▎ | 5/135 [00:05<01:27, 1.48it/s]
|
20 |
5%|▌ | 7/135 [00:05<00:54, 2.36it/s]
|
21 |
|
|
|
22 |
5%|▌ | 7/135 [00:05<00:54, 2.36it/s]
|
23 |
|
|
|
24 |
5%|▌ | 7/135 [00:05<00:54, 2.36it/s]
|
25 |
|
|
|
26 |
5%|▌ | 7/135 [00:05<00:54, 2.36it/s]
|
27 |
7%|▋ | 10/135 [00:05<00:30, 4.08it/s]
|
28 |
|
|
|
29 |
7%|▋ | 10/135 [00:05<00:30, 4.08it/s]
|
30 |
|
|
|
31 |
7%|▋ | 10/135 [00:05<00:30, 4.08it/s]
|
32 |
9%|▉ | 12/135 [00:05<00:24, 4.93it/s]
|
33 |
|
|
|
34 |
9%|▉ | 12/135 [00:05<00:24, 4.93it/s]
|
35 |
|
|
|
36 |
9%|▉ | 12/135 [00:05<00:24, 4.93it/s]
|
37 |
10%|█ | 14/135 [00:05<00:19, 6.36it/s]
|
38 |
|
|
|
39 |
10%|█ | 14/135 [00:05<00:19, 6.36it/s]
|
40 |
|
|
|
41 |
10%|█ | 14/135 [00:05<00:19, 6.36it/s]
|
42 |
|
|
|
43 |
10%|█ | 14/135 [00:05<00:19, 6.36it/s]
|
44 |
13%|█▎ | 17/135 [00:05<00:15, 7.70it/s]
|
45 |
|
|
|
46 |
13%|█▎ | 17/135 [00:05<00:15, 7.70it/s]
|
47 |
|
|
|
48 |
13%|█▎ | 17/135 [00:05<00:15, 7.70it/s]
|
49 |
|
|
|
50 |
13%|█▎ | 17/135 [00:06<00:15, 7.70it/s]
|
51 |
15%|█▍ | 20/135 [00:06<00:11, 10.40it/s]
|
52 |
|
|
|
53 |
15%|█▍ | 20/135 [00:06<00:11, 10.40it/s]
|
54 |
|
|
|
55 |
15%|█▍ | 20/135 [00:06<00:11, 10.40it/s]
|
56 |
|
|
|
57 |
15%|█▍ | 20/135 [00:06<00:11, 10.40it/s]
|
58 |
17%|█▋ | 23/135 [00:06<00:11, 10.16it/s]
|
59 |
|
|
|
60 |
17%|█▋ | 23/135 [00:06<00:11, 10.16it/s]
|
61 |
|
|
|
62 |
17%|█▋ | 23/135 [00:06<00:11, 10.16it/s]
|
63 |
|
|
|
64 |
17%|█▋ | 23/135 [00:06<00:11, 10.16it/s]
|
65 |
19%|█▉ | 26/135 [00:06<00:08, 12.86it/s]
|
66 |
|
|
|
67 |
19%|█▉ | 26/135 [00:06<00:08, 12.86it/s]
|
68 |
|
|
|
69 |
19%|█▉ | 26/135 [00:06<00:08, 12.86it/s]
|
70 |
|
|
|
71 |
19%|█▉ | 26/135 [00:06<00:08, 12.86it/s]
|
72 |
21%|██▏ | 29/135 [00:06<00:08, 12.28it/s]
|
73 |
|
|
|
74 |
21%|██▏ | 29/135 [00:06<00:08, 12.28it/s]
|
75 |
|
|
|
76 |
21%|██▏ | 29/135 [00:06<00:08, 12.28it/s]
|
77 |
|
|
|
78 |
21%|██▏ | 29/135 [00:06<00:08, 12.28it/s]
|
79 |
24%|██▎ | 32/135 [00:06<00:06, 14.78it/s]
|
80 |
|
|
|
81 |
24%|██▎ | 32/135 [00:06<00:06, 14.78it/s]
|
82 |
|
|
|
83 |
24%|██▎ | 32/135 [00:06<00:06, 14.78it/s]
|
84 |
|
|
|
85 |
24%|██▎ | 32/135 [00:07<00:06, 14.78it/s]
|
86 |
26%|██▌ | 35/135 [00:07<00:07, 12.60it/s]
|
87 |
|
|
|
88 |
26%|██▌ | 35/135 [00:07<00:07, 12.60it/s]
|
89 |
|
|
|
90 |
26%|██▌ | 35/135 [00:07<00:07, 12.60it/s]
|
91 |
|
|
|
92 |
26%|██▌ | 35/135 [00:07<00:07, 12.60it/s]
|
93 |
28%|██▊ | 38/135 [00:07<00:06, 15.07it/s]
|
94 |
|
|
|
95 |
28%|██▊ | 38/135 [00:07<00:06, 15.07it/s]
|
96 |
|
|
|
97 |
28%|██▊ | 38/135 [00:07<00:06, 15.07it/s]
|
98 |
|
|
|
99 |
28%|██▊ | 38/135 [00:07<00:06, 15.07it/s]
|
100 |
30%|███ | 41/135 [00:07<00:07, 13.33it/s]
|
101 |
|
|
|
102 |
30%|███ | 41/135 [00:07<00:07, 13.33it/s]
|
103 |
|
|
|
104 |
30%|███ | 41/135 [00:07<00:07, 13.33it/s]
|
105 |
|
|
|
106 |
30%|███ | 41/135 [00:07<00:07, 13.33it/s]
|
107 |
33%|███▎ | 44/135 [00:07<00:05, 15.58it/s]
|
108 |
|
|
|
109 |
33%|███▎ | 44/135 [00:07<00:05, 15.58it/s]
|
110 |
|
|
|
111 |
33%|███▎ | 44/135 [00:07<00:05, 15.58it/s]
|
112 |
|
|
|
113 |
33%|███▎ | 44/135 [00:07<00:05, 15.58it/s]
|
114 |
35%|███▍ | 47/135 [00:08<00:06, 13.02it/s]
|
115 |
|
|
|
116 |
35%|███▍ | 47/135 [00:08<00:06, 13.02it/s]
|
117 |
|
|
|
118 |
35%|███▍ | 47/135 [00:08<00:06, 13.02it/s]
|
119 |
|
|
|
120 |
35%|███▍ | 47/135 [00:08<00:06, 13.02it/s]
|
121 |
37%|███▋ | 50/135 [00:08<00:05, 15.39it/s]
|
122 |
|
|
|
123 |
37%|███▋ | 50/135 [00:08<00:05, 15.39it/s]
|
124 |
|
|
|
125 |
37%|███▋ | 50/135 [00:08<00:05, 15.39it/s]
|
126 |
|
|
|
127 |
37%|███▋ | 50/135 [00:08<00:05, 15.39it/s]
|
128 |
39%|███▉ | 53/135 [00:08<00:05, 13.68it/s]
|
129 |
|
|
|
130 |
39%|███▉ | 53/135 [00:08<00:05, 13.68it/s]
|
131 |
|
|
|
132 |
39%|███▉ | 53/135 [00:08<00:05, 13.68it/s]
|
133 |
|
|
|
134 |
39%|███▉ | 53/135 [00:08<00:05, 13.68it/s]
|
135 |
41%|████▏ | 56/135 [00:08<00:04, 15.94it/s]
|
136 |
|
|
|
137 |
41%|████▏ | 56/135 [00:08<00:04, 15.94it/s]
|
138 |
|
|
|
139 |
41%|████▏ | 56/135 [00:08<00:04, 15.94it/s]
|
140 |
|
|
|
141 |
41%|████▏ | 56/135 [00:08<00:04, 15.94it/s]
|
142 |
44%|████▎ | 59/135 [00:08<00:05, 13.32it/s]
|
143 |
|
|
|
144 |
44%|████▎ | 59/135 [00:08<00:05, 13.32it/s]
|
145 |
|
|
|
146 |
44%|████▎ | 59/135 [00:08<00:05, 13.32it/s]
|
147 |
|
|
|
148 |
44%|████▎ | 59/135 [00:08<00:05, 13.32it/s]
|
149 |
46%|████▌ | 62/135 [00:08<00:04, 15.85it/s]
|
150 |
|
|
|
151 |
46%|████▌ | 62/135 [00:08<00:04, 15.85it/s]
|
152 |
|
|
|
153 |
46%|████▌ | 62/135 [00:08<00:04, 15.85it/s]
|
154 |
|
|
|
155 |
46%|████▌ | 62/135 [00:09<00:04, 15.85it/s]
|
156 |
48%|████▊ | 65/135 [00:09<00:05, 13.89it/s]
|
157 |
|
|
|
158 |
48%|████▊ | 65/135 [00:09<00:05, 13.89it/s]
|
159 |
|
|
|
160 |
48%|████▊ | 65/135 [00:09<00:05, 13.89it/s]
|
161 |
|
|
|
162 |
48%|████▊ | 65/135 [00:09<00:05, 13.89it/s]
|
163 |
50%|█████ | 68/135 [00:09<00:04, 16.19it/s]
|
164 |
|
|
|
165 |
50%|█████ | 68/135 [00:09<00:04, 16.19it/s]
|
166 |
|
|
|
167 |
50%|█████ | 68/135 [00:09<00:04, 16.19it/s]
|
168 |
|
|
|
169 |
50%|█████ | 68/135 [00:09<00:04, 16.19it/s]
|
170 |
53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s]
|
171 |
|
|
|
172 |
53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s]
|
173 |
|
|
|
174 |
53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s]
|
175 |
|
|
|
176 |
53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s]
|
177 |
55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s]
|
178 |
|
|
|
179 |
55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s]
|
180 |
|
|
|
181 |
55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s]
|
182 |
|
|
|
183 |
55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s]
|
184 |
57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s]
|
185 |
|
|
|
186 |
57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s]
|
187 |
|
|
|
188 |
57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s]
|
189 |
|
|
|
190 |
57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s]
|
191 |
59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s]
|
192 |
|
|
|
193 |
59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s]
|
194 |
|
|
|
195 |
59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s]
|
196 |
|
|
|
197 |
59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s]
|
198 |
61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s]
|
199 |
|
|
|
200 |
61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s]
|
201 |
|
|
|
202 |
61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s]
|
203 |
|
|
|
204 |
61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s]
|
205 |
64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s]
|
206 |
|
|
|
207 |
64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s]
|
208 |
|
|
|
209 |
64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s]
|
210 |
|
|
|
211 |
64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s]
|
212 |
66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s]
|
213 |
|
|
|
214 |
66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s]
|
215 |
|
|
|
216 |
66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s]
|
217 |
|
|
|
218 |
66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s]
|
219 |
68%|██████▊ | 92/135 [00:10<00:02, 16.18it/s]
|
220 |
|
|
|
221 |
68%|██████▊ | 92/135 [00:10<00:02, 16.18it/s]
|
222 |
|
|
|
223 |
68%|██████▊ | 92/135 [00:10<00:02, 16.18it/s]
|
224 |
|
|
|
225 |
68%|██████▊ | 92/135 [00:11<00:02, 16.18it/s]
|
226 |
70%|███████ | 95/135 [00:11<00:02, 13.39it/s]
|
227 |
|
|
|
228 |
70%|███████ | 95/135 [00:11<00:02, 13.39it/s]
|
229 |
|
|
|
230 |
70%|███████ | 95/135 [00:11<00:02, 13.39it/s]
|
231 |
|
|
|
232 |
70%|███████ | 95/135 [00:11<00:02, 13.39it/s]
|
233 |
73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s]
|
234 |
|
|
|
235 |
73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s]
|
236 |
|
|
|
237 |
73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s]
|
238 |
|
|
|
239 |
73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s]
|
240 |
75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s]
|
241 |
|
|
|
242 |
75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s]
|
243 |
|
|
|
244 |
75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s]
|
245 |
|
|
|
246 |
75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s]
|
247 |
77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s]
|
248 |
|
|
|
249 |
77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s]
|
250 |
|
|
|
251 |
77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s]
|
252 |
|
|
|
253 |
77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s]
|
254 |
79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s]
|
255 |
|
|
|
256 |
79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s]
|
257 |
|
|
|
258 |
79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s]
|
259 |
|
|
|
260 |
79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s]
|
261 |
81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s]
|
262 |
|
|
|
263 |
81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s]
|
264 |
|
|
|
265 |
81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s]
|
266 |
|
|
|
267 |
81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s]
|
268 |
84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s]
|
269 |
|
|
|
270 |
84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s]
|
271 |
|
|
|
272 |
84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s]
|
273 |
|
|
|
274 |
84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s]
|
275 |
86%|████████▌ | 116/135 [00:12<00:01, 16.64it/s]
|
276 |
|
|
|
277 |
86%|████████▌ | 116/135 [00:12<00:01, 16.64it/s]
|
278 |
|
|
|
279 |
86%|██████���█▌ | 116/135 [00:12<00:01, 16.64it/s]
|
280 |
|
|
|
281 |
86%|████████▌ | 116/135 [00:12<00:01, 16.64it/s]
|
282 |
88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s]
|
283 |
|
|
|
284 |
88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s]
|
285 |
|
|
|
286 |
88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s]
|
287 |
|
|
|
288 |
88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s]
|
289 |
90%|█████████ | 122/135 [00:12<00:00, 16.30it/s]
|
290 |
|
|
|
291 |
90%|█████████ | 122/135 [00:12<00:00, 16.30it/s]
|
292 |
|
|
|
293 |
90%|█████████ | 122/135 [00:12<00:00, 16.30it/s]
|
294 |
|
|
|
295 |
90%|█████████ | 122/135 [00:13<00:00, 16.30it/s]
|
296 |
93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s]
|
297 |
|
|
|
298 |
93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s]
|
299 |
|
|
|
300 |
93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s]
|
301 |
|
|
|
302 |
93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s]
|
303 |
95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s]
|
304 |
|
|
|
305 |
95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s]
|
306 |
|
|
|
307 |
95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s]
|
308 |
|
|
|
309 |
95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s]
|
310 |
97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s]
|
311 |
|
|
|
312 |
97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s]
|
313 |
|
|
|
314 |
97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s]
|
315 |
|
|
|
316 |
97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s]
|
317 |
99%|█████████▉| 134/135 [00:13<00:00, 16.33it/s]
|
318 |
|
|
|
319 |
99%|█████████▉| 134/135 [00:13<00:00, 16.33it/s]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
/opt/conda/envs/py310/bin/python -m mlc_llm gen_config /models/TinyLlama-1.1B-Chat-v1.0 --quantization q0f16 --conv-template chatml --output /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC
|
2 |
+
[2024-06-04 20:08:25] INFO auto_config.py:116: [92mFound[0m model configuration: /models/TinyLlama-1.1B-Chat-v1.0/config.json
|
3 |
+
[2024-06-04 20:08:25] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
|
4 |
+
[2024-06-04 20:08:25] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (2048)
|
5 |
+
[2024-06-04 20:08:25] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048
|
6 |
+
[2024-06-04 20:08:25] INFO config.py:107: Overriding [1mmax_batch_size[0m from 1 to 80
|
7 |
+
[2024-06-04 20:08:25] INFO gen_config.py:143: [generation_config.json] Setting [1mbos_token_id[0m: 1
|
8 |
+
[2024-06-04 20:08:25] INFO gen_config.py:143: [generation_config.json] Setting [1meos_token_id[0m: 2
|
9 |
+
[2024-06-04 20:08:25] INFO gen_config.py:143: [generation_config.json] Setting [1mpad_token_id[0m: 0
|
10 |
+
[2024-06-04 20:08:25] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer.model. Copying to [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/tokenizer.model[0m
|
11 |
+
[2024-06-04 20:08:25] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/tokenizer.json[0m
|
12 |
+
[2024-06-04 20:08:25] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/vocab.json
|
13 |
+
[2024-06-04 20:08:25] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/merges.txt
|
14 |
+
[2024-06-04 20:08:25] INFO gen_config.py:157: [91mNot found[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/added_tokens.json
|
15 |
+
[2024-06-04 20:08:25] INFO gen_config.py:155: [92mFound[0m tokenizer config: /models/TinyLlama-1.1B-Chat-v1.0/tokenizer_config.json. Copying to [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/tokenizer_config.json[0m
|
16 |
+
[2024-06-04 20:08:25] INFO gen_config.py:216: Detected tokenizer info: {'token_postproc_method': 'byte_fallback', 'prepend_space_in_encode': True, 'strip_space_in_decode': True}
|
17 |
+
[2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mtemperature[0m: 1.0
|
18 |
+
[2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mpresence_penalty[0m: 0.0
|
19 |
+
[2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mfrequency_penalty[0m: 0.0
|
20 |
+
[2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mrepetition_penalty[0m: 1.0
|
21 |
+
[2024-06-04 20:08:25] INFO gen_config.py:32: [System default] Setting [1mtop_p[0m: 1.0
|
22 |
+
[2024-06-04 20:08:25] INFO gen_config.py:223: Dumping configuration file to: [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/mlc-chat-config.json[0m
|
23 |
+
/opt/conda/envs/py310/bin/python -m mlc_llm convert_weight /models/TinyLlama-1.1B-Chat-v1.0 --quantization q0f16 --output /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC
|
24 |
+
[2024-06-04 20:08:27] INFO auto_config.py:116: [92mFound[0m model configuration: /models/TinyLlama-1.1B-Chat-v1.0/config.json
|
25 |
+
[2024-06-04 20:08:28] INFO auto_device.py:79: [92mFound[0m device: cuda:0
|
26 |
+
[2024-06-04 20:08:30] INFO auto_device.py:88: [91mNot found[0m device: rocm:0
|
27 |
+
[2024-06-04 20:08:31] INFO auto_device.py:88: [91mNot found[0m device: metal:0
|
28 |
+
[2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:0
|
29 |
+
[2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:1
|
30 |
+
[2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:2
|
31 |
+
[2024-06-04 20:08:33] INFO auto_device.py:79: [92mFound[0m device: vulkan:3
|
32 |
+
[2024-06-04 20:08:34] INFO auto_device.py:88: [91mNot found[0m device: opencl:0
|
33 |
+
[2024-06-04 20:08:34] INFO auto_device.py:35: Using device: [1mcuda:0[0m
|
34 |
+
[2024-06-04 20:08:34] INFO auto_weight.py:71: Finding weights in: /models/TinyLlama-1.1B-Chat-v1.0
|
35 |
+
[2024-06-04 20:08:34] INFO auto_weight.py:137: [91mNot found[0m Huggingface PyTorch
|
36 |
+
[2024-06-04 20:08:34] INFO auto_weight.py:144: [92mFound[0m source weight format: huggingface-safetensor. Source configuration: /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json
|
37 |
+
[2024-06-04 20:08:34] INFO auto_weight.py:107: Using source weight configuration: [1m/models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json[0m. Use `--source` to override.
|
38 |
+
[2024-06-04 20:08:34] INFO auto_weight.py:111: Using source weight format: [1mhuggingface-safetensor[0m. Use `--source-format` to override.
|
39 |
+
[2024-06-04 20:08:34] INFO auto_config.py:154: [92mFound[0m model type: [1mllama[0m. Use `--model-type` to override.
|
40 |
+
[2024-06-04 20:08:34] INFO llama_model.py:52: [1mcontext_window_size[0m not found in config.json. Falling back to [1mmax_position_embeddings[0m (2048)
|
41 |
+
[2024-06-04 20:08:34] INFO llama_model.py:72: [1mprefill_chunk_size[0m defaults to 2048
|
42 |
+
[1mWeight conversion with arguments:[0m
|
43 |
+
[1m--config[0m /models/TinyLlama-1.1B-Chat-v1.0/config.json
|
44 |
+
[1m--quantization[0m NoQuantize(name='q0f16', kind='no-quant', model_dtype='float16')
|
45 |
+
[1m--model-type[0m llama
|
46 |
+
[1m--device[0m cuda:0
|
47 |
+
[1m--source[0m /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors.index.json
|
48 |
+
[1m--source-format[0m huggingface-safetensor
|
49 |
+
[1m--output[0m /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC
|
50 |
+
Start storing to cache /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC
|
51 |
+
|
52 |
0%| | 0/135 [00:00<?, ?it/s]
|
53 |
|
54 |
+
|
55 |
0%| | 0/135 [00:00<?, ?it/s]
|
56 |
|
57 |
+
|
58 |
0%| | 0/135 [00:03<?, ?it/s]
|
59 |
1%| | 1/135 [00:04<09:19, 4.17s/it]
|
60 |
|
61 |
+
|
62 |
1%| | 1/135 [00:04<09:19, 4.17s/it]
|
63 |
1%|▏ | 2/135 [00:04<04:37, 2.09s/it]
|
64 |
|
65 |
+
|
66 |
1%|▏ | 2/135 [00:04<04:37, 2.09s/it]
|
67 |
|
68 |
+
|
69 |
1%|▏ | 2/135 [00:04<04:37, 2.09s/it]
|
70 |
|
71 |
+
|
72 |
1%|▏ | 2/135 [00:04<04:37, 2.09s/it]
|
73 |
4%|▎ | 5/135 [00:05<01:27, 1.48it/s]
|
74 |
|
75 |
+
|
76 |
4%|▎ | 5/135 [00:05<01:27, 1.48it/s]
|
77 |
|
78 |
+
|
79 |
4%|▎ | 5/135 [00:05<01:27, 1.48it/s]
|
80 |
5%|▌ | 7/135 [00:05<00:54, 2.36it/s]
|
81 |
|
82 |
+
|
83 |
5%|▌ | 7/135 [00:05<00:54, 2.36it/s]
|
84 |
|
85 |
+
|
86 |
5%|▌ | 7/135 [00:05<00:54, 2.36it/s]
|
87 |
|
88 |
+
|
89 |
5%|▌ | 7/135 [00:05<00:54, 2.36it/s]
|
90 |
7%|▋ | 10/135 [00:05<00:30, 4.08it/s]
|
91 |
|
92 |
+
|
93 |
7%|▋ | 10/135 [00:05<00:30, 4.08it/s]
|
94 |
|
95 |
+
|
96 |
7%|▋ | 10/135 [00:05<00:30, 4.08it/s]
|
97 |
9%|▉ | 12/135 [00:05<00:24, 4.93it/s]
|
98 |
|
99 |
+
|
100 |
9%|▉ | 12/135 [00:05<00:24, 4.93it/s]
|
101 |
|
102 |
+
|
103 |
9%|▉ | 12/135 [00:05<00:24, 4.93it/s]
|
104 |
10%|█ | 14/135 [00:05<00:19, 6.36it/s]
|
105 |
|
106 |
+
|
107 |
10%|█ | 14/135 [00:05<00:19, 6.36it/s]
|
108 |
|
109 |
+
|
110 |
10%|█ | 14/135 [00:05<00:19, 6.36it/s]
|
111 |
|
112 |
+
|
113 |
10%|█ | 14/135 [00:05<00:19, 6.36it/s]
|
114 |
13%|█▎ | 17/135 [00:05<00:15, 7.70it/s]
|
115 |
|
116 |
+
|
117 |
13%|█▎ | 17/135 [00:05<00:15, 7.70it/s]
|
118 |
|
119 |
+
|
120 |
13%|█▎ | 17/135 [00:05<00:15, 7.70it/s]
|
121 |
|
122 |
+
|
123 |
13%|█▎ | 17/135 [00:06<00:15, 7.70it/s]
|
124 |
15%|█▍ | 20/135 [00:06<00:11, 10.40it/s]
|
125 |
|
126 |
+
|
127 |
15%|█▍ | 20/135 [00:06<00:11, 10.40it/s]
|
128 |
|
129 |
+
|
130 |
15%|█▍ | 20/135 [00:06<00:11, 10.40it/s]
|
131 |
|
132 |
+
|
133 |
15%|█▍ | 20/135 [00:06<00:11, 10.40it/s]
|
134 |
17%|█▋ | 23/135 [00:06<00:11, 10.16it/s]
|
135 |
|
136 |
+
|
137 |
17%|█▋ | 23/135 [00:06<00:11, 10.16it/s]
|
138 |
|
139 |
+
|
140 |
17%|█▋ | 23/135 [00:06<00:11, 10.16it/s]
|
141 |
|
142 |
+
|
143 |
17%|█▋ | 23/135 [00:06<00:11, 10.16it/s]
|
144 |
19%|█▉ | 26/135 [00:06<00:08, 12.86it/s]
|
145 |
|
146 |
+
|
147 |
19%|█▉ | 26/135 [00:06<00:08, 12.86it/s]
|
148 |
|
149 |
+
|
150 |
19%|█▉ | 26/135 [00:06<00:08, 12.86it/s]
|
151 |
|
152 |
+
|
153 |
19%|█▉ | 26/135 [00:06<00:08, 12.86it/s]
|
154 |
21%|██▏ | 29/135 [00:06<00:08, 12.28it/s]
|
155 |
|
156 |
+
|
157 |
21%|██▏ | 29/135 [00:06<00:08, 12.28it/s]
|
158 |
|
159 |
+
|
160 |
21%|██▏ | 29/135 [00:06<00:08, 12.28it/s]
|
161 |
|
162 |
+
|
163 |
21%|██▏ | 29/135 [00:06<00:08, 12.28it/s]
|
164 |
24%|██▎ | 32/135 [00:06<00:06, 14.78it/s]
|
165 |
|
166 |
+
|
167 |
24%|██▎ | 32/135 [00:06<00:06, 14.78it/s]
|
168 |
|
169 |
+
|
170 |
24%|██▎ | 32/135 [00:06<00:06, 14.78it/s]
|
171 |
|
172 |
+
|
173 |
24%|██▎ | 32/135 [00:07<00:06, 14.78it/s]
|
174 |
26%|██▌ | 35/135 [00:07<00:07, 12.60it/s]
|
175 |
|
176 |
+
|
177 |
26%|██▌ | 35/135 [00:07<00:07, 12.60it/s]
|
178 |
|
179 |
+
|
180 |
26%|██▌ | 35/135 [00:07<00:07, 12.60it/s]
|
181 |
|
182 |
+
|
183 |
26%|██▌ | 35/135 [00:07<00:07, 12.60it/s]
|
184 |
28%|██▊ | 38/135 [00:07<00:06, 15.07it/s]
|
185 |
|
186 |
+
|
187 |
28%|██▊ | 38/135 [00:07<00:06, 15.07it/s]
|
188 |
|
189 |
+
|
190 |
28%|██▊ | 38/135 [00:07<00:06, 15.07it/s]
|
191 |
|
192 |
+
|
193 |
28%|██▊ | 38/135 [00:07<00:06, 15.07it/s]
|
194 |
30%|███ | 41/135 [00:07<00:07, 13.33it/s]
|
195 |
|
196 |
+
|
197 |
30%|███ | 41/135 [00:07<00:07, 13.33it/s]
|
198 |
|
199 |
+
|
200 |
30%|███ | 41/135 [00:07<00:07, 13.33it/s]
|
201 |
|
202 |
+
|
203 |
30%|███ | 41/135 [00:07<00:07, 13.33it/s]
|
204 |
33%|███▎ | 44/135 [00:07<00:05, 15.58it/s]
|
205 |
|
206 |
+
|
207 |
33%|███▎ | 44/135 [00:07<00:05, 15.58it/s]
|
208 |
|
209 |
+
|
210 |
33%|███▎ | 44/135 [00:07<00:05, 15.58it/s]
|
211 |
|
212 |
+
|
213 |
33%|███▎ | 44/135 [00:07<00:05, 15.58it/s]
|
214 |
35%|███▍ | 47/135 [00:08<00:06, 13.02it/s]
|
215 |
|
216 |
+
|
217 |
35%|███▍ | 47/135 [00:08<00:06, 13.02it/s]
|
218 |
|
219 |
+
|
220 |
35%|███▍ | 47/135 [00:08<00:06, 13.02it/s]
|
221 |
|
222 |
+
|
223 |
35%|███▍ | 47/135 [00:08<00:06, 13.02it/s]
|
224 |
37%|███▋ | 50/135 [00:08<00:05, 15.39it/s]
|
225 |
|
226 |
+
|
227 |
37%|███▋ | 50/135 [00:08<00:05, 15.39it/s]
|
228 |
|
229 |
+
|
230 |
37%|███▋ | 50/135 [00:08<00:05, 15.39it/s]
|
231 |
|
232 |
+
|
233 |
37%|███▋ | 50/135 [00:08<00:05, 15.39it/s]
|
234 |
39%|███▉ | 53/135 [00:08<00:05, 13.68it/s]
|
235 |
|
236 |
+
|
237 |
39%|███▉ | 53/135 [00:08<00:05, 13.68it/s]
|
238 |
|
239 |
+
|
240 |
39%|███▉ | 53/135 [00:08<00:05, 13.68it/s]
|
241 |
|
242 |
+
|
243 |
39%|███▉ | 53/135 [00:08<00:05, 13.68it/s]
|
244 |
41%|████▏ | 56/135 [00:08<00:04, 15.94it/s]
|
245 |
|
246 |
+
|
247 |
41%|████▏ | 56/135 [00:08<00:04, 15.94it/s]
|
248 |
|
249 |
+
|
250 |
41%|████▏ | 56/135 [00:08<00:04, 15.94it/s]
|
251 |
|
252 |
+
|
253 |
41%|████▏ | 56/135 [00:08<00:04, 15.94it/s]
|
254 |
44%|████▎ | 59/135 [00:08<00:05, 13.32it/s]
|
255 |
|
256 |
+
|
257 |
44%|████▎ | 59/135 [00:08<00:05, 13.32it/s]
|
258 |
|
259 |
+
|
260 |
44%|████▎ | 59/135 [00:08<00:05, 13.32it/s]
|
261 |
|
262 |
+
|
263 |
44%|████▎ | 59/135 [00:08<00:05, 13.32it/s]
|
264 |
46%|████▌ | 62/135 [00:08<00:04, 15.85it/s]
|
265 |
|
266 |
+
|
267 |
46%|████▌ | 62/135 [00:08<00:04, 15.85it/s]
|
268 |
|
269 |
+
|
270 |
46%|████▌ | 62/135 [00:08<00:04, 15.85it/s]
|
271 |
|
272 |
+
|
273 |
46%|████▌ | 62/135 [00:09<00:04, 15.85it/s]
|
274 |
48%|████▊ | 65/135 [00:09<00:05, 13.89it/s]
|
275 |
|
276 |
+
|
277 |
48%|████▊ | 65/135 [00:09<00:05, 13.89it/s]
|
278 |
|
279 |
+
|
280 |
48%|████▊ | 65/135 [00:09<00:05, 13.89it/s]
|
281 |
|
282 |
+
|
283 |
48%|████▊ | 65/135 [00:09<00:05, 13.89it/s]
|
284 |
50%|█████ | 68/135 [00:09<00:04, 16.19it/s]
|
285 |
|
286 |
+
|
287 |
50%|█████ | 68/135 [00:09<00:04, 16.19it/s]
|
288 |
|
289 |
+
|
290 |
50%|█████ | 68/135 [00:09<00:04, 16.19it/s]
|
291 |
|
292 |
+
|
293 |
50%|█████ | 68/135 [00:09<00:04, 16.19it/s]
|
294 |
53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s]
|
295 |
|
296 |
+
|
297 |
53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s]
|
298 |
|
299 |
+
|
300 |
53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s]
|
301 |
|
302 |
+
|
303 |
53%|█████▎ | 71/135 [00:09<00:04, 13.33it/s]
|
304 |
55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s]
|
305 |
|
306 |
+
|
307 |
55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s]
|
308 |
|
309 |
+
|
310 |
55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s]
|
311 |
|
312 |
+
|
313 |
55%|█████▍ | 74/135 [00:09<00:03, 15.75it/s]
|
314 |
57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s]
|
315 |
|
316 |
+
|
317 |
57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s]
|
318 |
|
319 |
+
|
320 |
57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s]
|
321 |
|
322 |
+
|
323 |
57%|█████▋ | 77/135 [00:10<00:04, 13.94it/s]
|
324 |
59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s]
|
325 |
|
326 |
+
|
327 |
59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s]
|
328 |
|
329 |
+
|
330 |
59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s]
|
331 |
|
332 |
+
|
333 |
59%|█████▉ | 80/135 [00:10<00:03, 16.18it/s]
|
334 |
61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s]
|
335 |
|
336 |
+
|
337 |
61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s]
|
338 |
|
339 |
+
|
340 |
61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s]
|
341 |
|
342 |
+
|
343 |
61%|██████▏ | 83/135 [00:10<00:03, 13.47it/s]
|
344 |
64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s]
|
345 |
|
346 |
+
|
347 |
64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s]
|
348 |
|
349 |
+
|
350 |
64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s]
|
351 |
|
352 |
+
|
353 |
64%|██████▎ | 86/135 [00:10<00:03, 15.99it/s]
|
354 |
66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s]
|
355 |
|
356 |
+
|
357 |
66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s]
|
358 |
|
359 |
+
|
360 |
66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s]
|
361 |
|
362 |
+
|
363 |
66%|██████▌ | 89/135 [00:10<00:03, 13.88it/s]
|
364 |
68%|██████▊ | 92/135 [00:10<00:02, 16.18it/s]
|
365 |
|
366 |
+
|
367 |
68%|██████▊ | 92/135 [00:10<00:02, 16.18it/s]
|
368 |
|
369 |
+
|
370 |
68%|██████▊ | 92/135 [00:10<00:02, 16.18it/s]
|
371 |
|
372 |
+
|
373 |
68%|██████▊ | 92/135 [00:11<00:02, 16.18it/s]
|
374 |
70%|███████ | 95/135 [00:11<00:02, 13.39it/s]
|
375 |
|
376 |
+
|
377 |
70%|███████ | 95/135 [00:11<00:02, 13.39it/s]
|
378 |
|
379 |
+
|
380 |
70%|███████ | 95/135 [00:11<00:02, 13.39it/s]
|
381 |
|
382 |
+
|
383 |
70%|███████ | 95/135 [00:11<00:02, 13.39it/s]
|
384 |
73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s]
|
385 |
|
386 |
+
|
387 |
73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s]
|
388 |
|
389 |
+
|
390 |
73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s]
|
391 |
|
392 |
+
|
393 |
73%|███████▎ | 98/135 [00:11<00:02, 15.88it/s]
|
394 |
75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s]
|
395 |
|
396 |
+
|
397 |
75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s]
|
398 |
|
399 |
+
|
400 |
75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s]
|
401 |
|
402 |
+
|
403 |
75%|███████▍ | 101/135 [00:11<00:02, 14.11it/s]
|
404 |
77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s]
|
405 |
|
406 |
+
|
407 |
77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s]
|
408 |
|
409 |
+
|
410 |
77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s]
|
411 |
|
412 |
+
|
413 |
77%|███████▋ | 104/135 [00:11<00:01, 16.40it/s]
|
414 |
79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s]
|
415 |
|
416 |
+
|
417 |
79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s]
|
418 |
|
419 |
+
|
420 |
79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s]
|
421 |
|
422 |
+
|
423 |
79%|███████▉ | 107/135 [00:12<00:02, 13.62it/s]
|
424 |
81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s]
|
425 |
|
426 |
+
|
427 |
81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s]
|
428 |
|
429 |
+
|
430 |
81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s]
|
431 |
|
432 |
+
|
433 |
81%|████████▏ | 110/135 [00:12<00:01, 16.17it/s]
|
434 |
84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s]
|
435 |
|
436 |
+
|
437 |
84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s]
|
438 |
|
439 |
+
|
440 |
84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s]
|
441 |
|
442 |
+
|
443 |
84%|████████▎ | 113/135 [00:12<00:01, 14.29it/s]
|
444 |
86%|████████▌ | 116/135 [00:12<00:01, 16.64it/s]
|
445 |
|
446 |
+
|
447 |
86%|████████▌ | 116/135 [00:12<00:01, 16.64it/s]
|
448 |
|
449 |
+
|
450 |
86%|██████���█▌ | 116/135 [00:12<00:01, 16.64it/s]
|
451 |
|
452 |
+
|
453 |
86%|████████▌ | 116/135 [00:12<00:01, 16.64it/s]
|
454 |
88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s]
|
455 |
|
456 |
+
|
457 |
88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s]
|
458 |
|
459 |
+
|
460 |
88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s]
|
461 |
|
462 |
+
|
463 |
88%|████████▊ | 119/135 [00:12<00:01, 13.75it/s]
|
464 |
90%|█████████ | 122/135 [00:12<00:00, 16.30it/s]
|
465 |
|
466 |
+
|
467 |
90%|█████████ | 122/135 [00:12<00:00, 16.30it/s]
|
468 |
|
469 |
+
|
470 |
90%|█████████ | 122/135 [00:12<00:00, 16.30it/s]
|
471 |
|
472 |
+
|
473 |
90%|█████████ | 122/135 [00:13<00:00, 16.30it/s]
|
474 |
93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s]
|
475 |
|
476 |
+
|
477 |
93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s]
|
478 |
|
479 |
+
|
480 |
93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s]
|
481 |
|
482 |
+
|
483 |
93%|█████████▎| 125/135 [00:13<00:00, 14.36it/s]
|
484 |
95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s]
|
485 |
|
486 |
+
|
487 |
95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s]
|
488 |
|
489 |
+
|
490 |
95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s]
|
491 |
|
492 |
+
|
493 |
95%|█████████▍| 128/135 [00:13<00:00, 16.75it/s]
|
494 |
97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s]
|
495 |
|
496 |
+
|
497 |
97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s]
|
498 |
|
499 |
+
|
500 |
97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s]
|
501 |
|
502 |
+
|
503 |
97%|█████████▋| 131/135 [00:13<00:00, 13.76it/s]
|
504 |
99%|█████████▉| 134/135 [00:13<00:00, 16.33it/s]
|
505 |
|
506 |
+
|
507 |
99%|█████████▉| 134/135 [00:13<00:00, 16.33it/s]
|
508 |
+
[2024-06-04 20:08:49] INFO huggingface_loader.py:197: Unloading HF weight file: /models/TinyLlama-1.1B-Chat-v1.0/model.safetensors
|
509 |
+
[2024-06-04 20:08:50] INFO stats.py:77: [92mTime usage[0m: HF loading: 3.678 sec; Pre-quantization mapping: 4.070 sec; Quantization: 0.000 sec
|
510 |
+
[2024-06-04 20:08:50] INFO stats.py:91: [92mRAM usage[0m: Peak RAM: 4.098 GB. Total bytes loaded from disk: 4.098 GB
|
511 |
+
[2024-06-04 20:08:50] INFO convert_weight.py:155: [92mParameter size[0m after quantization: 2.049 GB
|
512 |
+
[2024-06-04 20:08:50] INFO convert_weight.py:160: [92mTotal parameters[0m: 1,100,048,384
|
513 |
+
[2024-06-04 20:08:50] INFO convert_weight.py:161: [92mBits per parameter[0m: 16.000
|
514 |
+
[2024-06-04 20:08:50] INFO convert_weight.py:166: Saved to directory: [1m/models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC[0m
|
515 |
+
|
516 |
+
All finished, 58 total shards committed, record saved to /models/mlc-delivery/hf/mlc-ai/TinyLlama-1.1B-Chat-v1.0-q0f16-MLC/ndarray-cache.json
|
mlc-chat-config.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "0.1.0",
|
3 |
+
"model_type": "llama",
|
4 |
+
"quantization": "q0f16",
|
5 |
+
"model_config": {
|
6 |
+
"hidden_size": 2048,
|
7 |
+
"intermediate_size": 5632,
|
8 |
+
"num_attention_heads": 32,
|
9 |
+
"num_hidden_layers": 22,
|
10 |
+
"rms_norm_eps": 1e-05,
|
11 |
+
"vocab_size": 32000,
|
12 |
+
"position_embedding_base": 10000.0,
|
13 |
+
"context_window_size": 2048,
|
14 |
+
"prefill_chunk_size": 2048,
|
15 |
+
"num_key_value_heads": 4,
|
16 |
+
"head_dim": 64,
|
17 |
+
"tensor_parallel_shards": 1,
|
18 |
+
"max_batch_size": 80
|
19 |
+
},
|
20 |
+
"vocab_size": 32000,
|
21 |
+
"context_window_size": 2048,
|
22 |
+
"sliding_window_size": -1,
|
23 |
+
"prefill_chunk_size": 2048,
|
24 |
+
"attention_sink_size": -1,
|
25 |
+
"tensor_parallel_shards": 1,
|
26 |
+
"temperature": 1.0,
|
27 |
+
"presence_penalty": 0.0,
|
28 |
+
"frequency_penalty": 0.0,
|
29 |
+
"repetition_penalty": 1.0,
|
30 |
+
"top_p": 1.0,
|
31 |
+
"tokenizer_files": [
|
32 |
+
"tokenizer.model",
|
33 |
+
"tokenizer.json",
|
34 |
+
"tokenizer_config.json"
|
35 |
+
],
|
36 |
+
"tokenizer_info": {
|
37 |
+
"token_postproc_method": "byte_fallback",
|
38 |
+
"prepend_space_in_encode": true,
|
39 |
+
"strip_space_in_decode": true
|
40 |
+
},
|
41 |
+
"conv_template": {
|
42 |
+
"name": "chatml",
|
43 |
+
"system_template": "<|im_start|>system\n{system_message}",
|
44 |
+
"system_message": "A conversation between a user and an LLM-based AI assistant. The assistant gives helpful and honest answers.",
|
45 |
+
"system_prefix_token_ids": null,
|
46 |
+
"add_role_after_system_message": true,
|
47 |
+
"roles": {
|
48 |
+
"user": "<|im_start|>user",
|
49 |
+
"assistant": "<|im_start|>assistant"
|
50 |
+
},
|
51 |
+
"role_templates": {
|
52 |
+
"user": "{user_message}",
|
53 |
+
"assistant": "{assistant_message}",
|
54 |
+
"tool": "{tool_message}"
|
55 |
+
},
|
56 |
+
"messages": [],
|
57 |
+
"seps": [
|
58 |
+
"<|im_end|>\n"
|
59 |
+
],
|
60 |
+
"role_content_sep": "\n",
|
61 |
+
"role_empty_sep": "\n",
|
62 |
+
"stop_str": [
|
63 |
+
"<|im_end|>"
|
64 |
+
],
|
65 |
+
"stop_token_ids": [
|
66 |
+
2
|
67 |
+
],
|
68 |
+
"function_string": "",
|
69 |
+
"use_function_calling": false
|
70 |
+
},
|
71 |
+
"pad_token_id": 0,
|
72 |
+
"bos_token_id": 1,
|
73 |
+
"eos_token_id": 2
|
74 |
+
}
|
ndarray-cache.json
ADDED
@@ -0,0 +1,1913 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"ParamSize": 135,
|
4 |
+
"ParamBytes": 2200096768.0,
|
5 |
+
"BitsPerParam": 16.0
|
6 |
+
},
|
7 |
+
"records": [
|
8 |
+
{
|
9 |
+
"dataPath": "params_shard_0.bin",
|
10 |
+
"format": "raw-shard",
|
11 |
+
"nbytes": 131072000,
|
12 |
+
"records": [
|
13 |
+
{
|
14 |
+
"name": "lm_head.weight",
|
15 |
+
"shape": [
|
16 |
+
32000,
|
17 |
+
2048
|
18 |
+
],
|
19 |
+
"dtype": "float16",
|
20 |
+
"format": "f32-to-bf16",
|
21 |
+
"nbytes": 131072000,
|
22 |
+
"byteOffset": 0
|
23 |
+
}
|
24 |
+
],
|
25 |
+
"md5sum": "2c912eb53da81bf4ed798392c6dca9c1"
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"dataPath": "params_shard_1.bin",
|
29 |
+
"format": "raw-shard",
|
30 |
+
"nbytes": 131072000,
|
31 |
+
"records": [
|
32 |
+
{
|
33 |
+
"name": "model.embed_tokens.weight",
|
34 |
+
"shape": [
|
35 |
+
32000,
|
36 |
+
2048
|
37 |
+
],
|
38 |
+
"dtype": "float16",
|
39 |
+
"format": "f32-to-bf16",
|
40 |
+
"nbytes": 131072000,
|
41 |
+
"byteOffset": 0
|
42 |
+
}
|
43 |
+
],
|
44 |
+
"md5sum": "399f96b720d3722787e4b4c53153db38"
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"dataPath": "params_shard_2.bin",
|
48 |
+
"format": "raw-shard",
|
49 |
+
"nbytes": 46137344,
|
50 |
+
"records": [
|
51 |
+
{
|
52 |
+
"name": "model.layers.0.mlp.gate_up_proj.weight",
|
53 |
+
"shape": [
|
54 |
+
11264,
|
55 |
+
2048
|
56 |
+
],
|
57 |
+
"dtype": "float16",
|
58 |
+
"format": "f32-to-bf16",
|
59 |
+
"nbytes": 46137344,
|
60 |
+
"byteOffset": 0
|
61 |
+
}
|
62 |
+
],
|
63 |
+
"md5sum": "fa34e6caf91e51df6af120a36c719b67"
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"dataPath": "params_shard_3.bin",
|
67 |
+
"format": "raw-shard",
|
68 |
+
"nbytes": 23076864,
|
69 |
+
"records": [
|
70 |
+
{
|
71 |
+
"name": "model.layers.0.input_layernorm.weight",
|
72 |
+
"shape": [
|
73 |
+
2048
|
74 |
+
],
|
75 |
+
"dtype": "float16",
|
76 |
+
"format": "f32-to-bf16",
|
77 |
+
"nbytes": 4096,
|
78 |
+
"byteOffset": 0
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"name": "model.layers.0.mlp.down_proj.weight",
|
82 |
+
"shape": [
|
83 |
+
2048,
|
84 |
+
5632
|
85 |
+
],
|
86 |
+
"dtype": "float16",
|
87 |
+
"format": "f32-to-bf16",
|
88 |
+
"nbytes": 23068672,
|
89 |
+
"byteOffset": 4096
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"name": "model.layers.0.post_attention_layernorm.weight",
|
93 |
+
"shape": [
|
94 |
+
2048
|
95 |
+
],
|
96 |
+
"dtype": "float16",
|
97 |
+
"format": "f32-to-bf16",
|
98 |
+
"nbytes": 4096,
|
99 |
+
"byteOffset": 23072768
|
100 |
+
}
|
101 |
+
],
|
102 |
+
"md5sum": "665b16451cd7819f9459d97fcd4b636f"
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"dataPath": "params_shard_4.bin",
|
106 |
+
"format": "raw-shard",
|
107 |
+
"nbytes": 23068672,
|
108 |
+
"records": [
|
109 |
+
{
|
110 |
+
"name": "model.layers.1.mlp.down_proj.weight",
|
111 |
+
"shape": [
|
112 |
+
2048,
|
113 |
+
5632
|
114 |
+
],
|
115 |
+
"dtype": "float16",
|
116 |
+
"format": "f32-to-bf16",
|
117 |
+
"nbytes": 23068672,
|
118 |
+
"byteOffset": 0
|
119 |
+
}
|
120 |
+
],
|
121 |
+
"md5sum": "37ef5fa415ad986ab51a66a416aa038f"
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"dataPath": "params_shard_5.bin",
|
125 |
+
"format": "raw-shard",
|
126 |
+
"nbytes": 46137344,
|
127 |
+
"records": [
|
128 |
+
{
|
129 |
+
"name": "model.layers.1.mlp.gate_up_proj.weight",
|
130 |
+
"shape": [
|
131 |
+
11264,
|
132 |
+
2048
|
133 |
+
],
|
134 |
+
"dtype": "float16",
|
135 |
+
"format": "f32-to-bf16",
|
136 |
+
"nbytes": 46137344,
|
137 |
+
"byteOffset": 0
|
138 |
+
}
|
139 |
+
],
|
140 |
+
"md5sum": "49ef987668ce623867490def5af22e42"
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"dataPath": "params_shard_6.bin",
|
144 |
+
"format": "raw-shard",
|
145 |
+
"nbytes": 29368320,
|
146 |
+
"records": [
|
147 |
+
{
|
148 |
+
"name": "model.layers.0.self_attn.qkv_proj.weight",
|
149 |
+
"shape": [
|
150 |
+
2560,
|
151 |
+
2048
|
152 |
+
],
|
153 |
+
"dtype": "float16",
|
154 |
+
"format": "f32-to-bf16",
|
155 |
+
"nbytes": 10485760,
|
156 |
+
"byteOffset": 0
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"name": "model.layers.0.self_attn.o_proj.weight",
|
160 |
+
"shape": [
|
161 |
+
2048,
|
162 |
+
2048
|
163 |
+
],
|
164 |
+
"dtype": "float16",
|
165 |
+
"format": "f32-to-bf16",
|
166 |
+
"nbytes": 8388608,
|
167 |
+
"byteOffset": 10485760
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"name": "model.layers.1.input_layernorm.weight",
|
171 |
+
"shape": [
|
172 |
+
2048
|
173 |
+
],
|
174 |
+
"dtype": "float16",
|
175 |
+
"format": "f32-to-bf16",
|
176 |
+
"nbytes": 4096,
|
177 |
+
"byteOffset": 18874368
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"name": "model.layers.1.post_attention_layernorm.weight",
|
181 |
+
"shape": [
|
182 |
+
2048
|
183 |
+
],
|
184 |
+
"dtype": "float16",
|
185 |
+
"format": "f32-to-bf16",
|
186 |
+
"nbytes": 4096,
|
187 |
+
"byteOffset": 18878464
|
188 |
+
},
|
189 |
+
{
|
190 |
+
"name": "model.layers.1.self_attn.qkv_proj.weight",
|
191 |
+
"shape": [
|
192 |
+
2560,
|
193 |
+
2048
|
194 |
+
],
|
195 |
+
"dtype": "float16",
|
196 |
+
"format": "f32-to-bf16",
|
197 |
+
"nbytes": 10485760,
|
198 |
+
"byteOffset": 18882560
|
199 |
+
}
|
200 |
+
],
|
201 |
+
"md5sum": "1c03cee852f757a5effe5031f62d898d"
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"dataPath": "params_shard_7.bin",
|
205 |
+
"format": "raw-shard",
|
206 |
+
"nbytes": 46137344,
|
207 |
+
"records": [
|
208 |
+
{
|
209 |
+
"name": "model.layers.10.mlp.gate_up_proj.weight",
|
210 |
+
"shape": [
|
211 |
+
11264,
|
212 |
+
2048
|
213 |
+
],
|
214 |
+
"dtype": "float16",
|
215 |
+
"format": "f32-to-bf16",
|
216 |
+
"nbytes": 46137344,
|
217 |
+
"byteOffset": 0
|
218 |
+
}
|
219 |
+
],
|
220 |
+
"md5sum": "e0c42e6afb9acc2f06493b4b7ea8b697"
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"dataPath": "params_shard_8.bin",
|
224 |
+
"format": "raw-shard",
|
225 |
+
"nbytes": 31465472,
|
226 |
+
"records": [
|
227 |
+
{
|
228 |
+
"name": "model.layers.1.self_attn.o_proj.weight",
|
229 |
+
"shape": [
|
230 |
+
2048,
|
231 |
+
2048
|
232 |
+
],
|
233 |
+
"dtype": "float16",
|
234 |
+
"format": "f32-to-bf16",
|
235 |
+
"nbytes": 8388608,
|
236 |
+
"byteOffset": 0
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"name": "model.layers.10.input_layernorm.weight",
|
240 |
+
"shape": [
|
241 |
+
2048
|
242 |
+
],
|
243 |
+
"dtype": "float16",
|
244 |
+
"format": "f32-to-bf16",
|
245 |
+
"nbytes": 4096,
|
246 |
+
"byteOffset": 8388608
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"name": "model.layers.10.mlp.down_proj.weight",
|
250 |
+
"shape": [
|
251 |
+
2048,
|
252 |
+
5632
|
253 |
+
],
|
254 |
+
"dtype": "float16",
|
255 |
+
"format": "f32-to-bf16",
|
256 |
+
"nbytes": 23068672,
|
257 |
+
"byteOffset": 8392704
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"name": "model.layers.10.post_attention_layernorm.weight",
|
261 |
+
"shape": [
|
262 |
+
2048
|
263 |
+
],
|
264 |
+
"dtype": "float16",
|
265 |
+
"format": "f32-to-bf16",
|
266 |
+
"nbytes": 4096,
|
267 |
+
"byteOffset": 31461376
|
268 |
+
}
|
269 |
+
],
|
270 |
+
"md5sum": "3919996e166c175913687b3011a638bf"
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"dataPath": "params_shard_9.bin",
|
274 |
+
"format": "raw-shard",
|
275 |
+
"nbytes": 23068672,
|
276 |
+
"records": [
|
277 |
+
{
|
278 |
+
"name": "model.layers.11.mlp.down_proj.weight",
|
279 |
+
"shape": [
|
280 |
+
2048,
|
281 |
+
5632
|
282 |
+
],
|
283 |
+
"dtype": "float16",
|
284 |
+
"format": "f32-to-bf16",
|
285 |
+
"nbytes": 23068672,
|
286 |
+
"byteOffset": 0
|
287 |
+
}
|
288 |
+
],
|
289 |
+
"md5sum": "17f611d549b98636fd7a2cc677eafaf7"
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"dataPath": "params_shard_10.bin",
|
293 |
+
"format": "raw-shard",
|
294 |
+
"nbytes": 46137344,
|
295 |
+
"records": [
|
296 |
+
{
|
297 |
+
"name": "model.layers.11.mlp.gate_up_proj.weight",
|
298 |
+
"shape": [
|
299 |
+
11264,
|
300 |
+
2048
|
301 |
+
],
|
302 |
+
"dtype": "float16",
|
303 |
+
"format": "f32-to-bf16",
|
304 |
+
"nbytes": 46137344,
|
305 |
+
"byteOffset": 0
|
306 |
+
}
|
307 |
+
],
|
308 |
+
"md5sum": "5546632bd7f9edcbbea1997360360f51"
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"dataPath": "params_shard_11.bin",
|
312 |
+
"format": "raw-shard",
|
313 |
+
"nbytes": 29368320,
|
314 |
+
"records": [
|
315 |
+
{
|
316 |
+
"name": "model.layers.10.self_attn.qkv_proj.weight",
|
317 |
+
"shape": [
|
318 |
+
2560,
|
319 |
+
2048
|
320 |
+
],
|
321 |
+
"dtype": "float16",
|
322 |
+
"format": "f32-to-bf16",
|
323 |
+
"nbytes": 10485760,
|
324 |
+
"byteOffset": 0
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"name": "model.layers.10.self_attn.o_proj.weight",
|
328 |
+
"shape": [
|
329 |
+
2048,
|
330 |
+
2048
|
331 |
+
],
|
332 |
+
"dtype": "float16",
|
333 |
+
"format": "f32-to-bf16",
|
334 |
+
"nbytes": 8388608,
|
335 |
+
"byteOffset": 10485760
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"name": "model.layers.11.input_layernorm.weight",
|
339 |
+
"shape": [
|
340 |
+
2048
|
341 |
+
],
|
342 |
+
"dtype": "float16",
|
343 |
+
"format": "f32-to-bf16",
|
344 |
+
"nbytes": 4096,
|
345 |
+
"byteOffset": 18874368
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"name": "model.layers.11.post_attention_layernorm.weight",
|
349 |
+
"shape": [
|
350 |
+
2048
|
351 |
+
],
|
352 |
+
"dtype": "float16",
|
353 |
+
"format": "f32-to-bf16",
|
354 |
+
"nbytes": 4096,
|
355 |
+
"byteOffset": 18878464
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"name": "model.layers.11.self_attn.qkv_proj.weight",
|
359 |
+
"shape": [
|
360 |
+
2560,
|
361 |
+
2048
|
362 |
+
],
|
363 |
+
"dtype": "float16",
|
364 |
+
"format": "f32-to-bf16",
|
365 |
+
"nbytes": 10485760,
|
366 |
+
"byteOffset": 18882560
|
367 |
+
}
|
368 |
+
],
|
369 |
+
"md5sum": "35b557a4c14190f9b1cd4f8766a7f98d"
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"dataPath": "params_shard_12.bin",
|
373 |
+
"format": "raw-shard",
|
374 |
+
"nbytes": 46137344,
|
375 |
+
"records": [
|
376 |
+
{
|
377 |
+
"name": "model.layers.12.mlp.gate_up_proj.weight",
|
378 |
+
"shape": [
|
379 |
+
11264,
|
380 |
+
2048
|
381 |
+
],
|
382 |
+
"dtype": "float16",
|
383 |
+
"format": "f32-to-bf16",
|
384 |
+
"nbytes": 46137344,
|
385 |
+
"byteOffset": 0
|
386 |
+
}
|
387 |
+
],
|
388 |
+
"md5sum": "c5b76239603150d360630794c8d00e51"
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"dataPath": "params_shard_13.bin",
|
392 |
+
"format": "raw-shard",
|
393 |
+
"nbytes": 31465472,
|
394 |
+
"records": [
|
395 |
+
{
|
396 |
+
"name": "model.layers.11.self_attn.o_proj.weight",
|
397 |
+
"shape": [
|
398 |
+
2048,
|
399 |
+
2048
|
400 |
+
],
|
401 |
+
"dtype": "float16",
|
402 |
+
"format": "f32-to-bf16",
|
403 |
+
"nbytes": 8388608,
|
404 |
+
"byteOffset": 0
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"name": "model.layers.12.input_layernorm.weight",
|
408 |
+
"shape": [
|
409 |
+
2048
|
410 |
+
],
|
411 |
+
"dtype": "float16",
|
412 |
+
"format": "f32-to-bf16",
|
413 |
+
"nbytes": 4096,
|
414 |
+
"byteOffset": 8388608
|
415 |
+
},
|
416 |
+
{
|
417 |
+
"name": "model.layers.12.mlp.down_proj.weight",
|
418 |
+
"shape": [
|
419 |
+
2048,
|
420 |
+
5632
|
421 |
+
],
|
422 |
+
"dtype": "float16",
|
423 |
+
"format": "f32-to-bf16",
|
424 |
+
"nbytes": 23068672,
|
425 |
+
"byteOffset": 8392704
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"name": "model.layers.12.post_attention_layernorm.weight",
|
429 |
+
"shape": [
|
430 |
+
2048
|
431 |
+
],
|
432 |
+
"dtype": "float16",
|
433 |
+
"format": "f32-to-bf16",
|
434 |
+
"nbytes": 4096,
|
435 |
+
"byteOffset": 31461376
|
436 |
+
}
|
437 |
+
],
|
438 |
+
"md5sum": "eb45fd07423c9ef8bdd2594bfb82aadb"
|
439 |
+
},
|
440 |
+
{
|
441 |
+
"dataPath": "params_shard_14.bin",
|
442 |
+
"format": "raw-shard",
|
443 |
+
"nbytes": 23068672,
|
444 |
+
"records": [
|
445 |
+
{
|
446 |
+
"name": "model.layers.13.mlp.down_proj.weight",
|
447 |
+
"shape": [
|
448 |
+
2048,
|
449 |
+
5632
|
450 |
+
],
|
451 |
+
"dtype": "float16",
|
452 |
+
"format": "f32-to-bf16",
|
453 |
+
"nbytes": 23068672,
|
454 |
+
"byteOffset": 0
|
455 |
+
}
|
456 |
+
],
|
457 |
+
"md5sum": "549207afa7495fd9633b2bcb505290da"
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"dataPath": "params_shard_15.bin",
|
461 |
+
"format": "raw-shard",
|
462 |
+
"nbytes": 46137344,
|
463 |
+
"records": [
|
464 |
+
{
|
465 |
+
"name": "model.layers.13.mlp.gate_up_proj.weight",
|
466 |
+
"shape": [
|
467 |
+
11264,
|
468 |
+
2048
|
469 |
+
],
|
470 |
+
"dtype": "float16",
|
471 |
+
"format": "f32-to-bf16",
|
472 |
+
"nbytes": 46137344,
|
473 |
+
"byteOffset": 0
|
474 |
+
}
|
475 |
+
],
|
476 |
+
"md5sum": "5647a65140d6c8b4f4822d23503c8a0c"
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"dataPath": "params_shard_16.bin",
|
480 |
+
"format": "raw-shard",
|
481 |
+
"nbytes": 29368320,
|
482 |
+
"records": [
|
483 |
+
{
|
484 |
+
"name": "model.layers.12.self_attn.qkv_proj.weight",
|
485 |
+
"shape": [
|
486 |
+
2560,
|
487 |
+
2048
|
488 |
+
],
|
489 |
+
"dtype": "float16",
|
490 |
+
"format": "f32-to-bf16",
|
491 |
+
"nbytes": 10485760,
|
492 |
+
"byteOffset": 0
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"name": "model.layers.12.self_attn.o_proj.weight",
|
496 |
+
"shape": [
|
497 |
+
2048,
|
498 |
+
2048
|
499 |
+
],
|
500 |
+
"dtype": "float16",
|
501 |
+
"format": "f32-to-bf16",
|
502 |
+
"nbytes": 8388608,
|
503 |
+
"byteOffset": 10485760
|
504 |
+
},
|
505 |
+
{
|
506 |
+
"name": "model.layers.13.input_layernorm.weight",
|
507 |
+
"shape": [
|
508 |
+
2048
|
509 |
+
],
|
510 |
+
"dtype": "float16",
|
511 |
+
"format": "f32-to-bf16",
|
512 |
+
"nbytes": 4096,
|
513 |
+
"byteOffset": 18874368
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"name": "model.layers.13.post_attention_layernorm.weight",
|
517 |
+
"shape": [
|
518 |
+
2048
|
519 |
+
],
|
520 |
+
"dtype": "float16",
|
521 |
+
"format": "f32-to-bf16",
|
522 |
+
"nbytes": 4096,
|
523 |
+
"byteOffset": 18878464
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"name": "model.layers.13.self_attn.qkv_proj.weight",
|
527 |
+
"shape": [
|
528 |
+
2560,
|
529 |
+
2048
|
530 |
+
],
|
531 |
+
"dtype": "float16",
|
532 |
+
"format": "f32-to-bf16",
|
533 |
+
"nbytes": 10485760,
|
534 |
+
"byteOffset": 18882560
|
535 |
+
}
|
536 |
+
],
|
537 |
+
"md5sum": "6adfbc4e603f8276d5955c143c88de13"
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"dataPath": "params_shard_17.bin",
|
541 |
+
"format": "raw-shard",
|
542 |
+
"nbytes": 46137344,
|
543 |
+
"records": [
|
544 |
+
{
|
545 |
+
"name": "model.layers.14.mlp.gate_up_proj.weight",
|
546 |
+
"shape": [
|
547 |
+
11264,
|
548 |
+
2048
|
549 |
+
],
|
550 |
+
"dtype": "float16",
|
551 |
+
"format": "f32-to-bf16",
|
552 |
+
"nbytes": 46137344,
|
553 |
+
"byteOffset": 0
|
554 |
+
}
|
555 |
+
],
|
556 |
+
"md5sum": "208c2247e69e1af227cb0763f1585adf"
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"dataPath": "params_shard_18.bin",
|
560 |
+
"format": "raw-shard",
|
561 |
+
"nbytes": 31465472,
|
562 |
+
"records": [
|
563 |
+
{
|
564 |
+
"name": "model.layers.13.self_attn.o_proj.weight",
|
565 |
+
"shape": [
|
566 |
+
2048,
|
567 |
+
2048
|
568 |
+
],
|
569 |
+
"dtype": "float16",
|
570 |
+
"format": "f32-to-bf16",
|
571 |
+
"nbytes": 8388608,
|
572 |
+
"byteOffset": 0
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"name": "model.layers.14.input_layernorm.weight",
|
576 |
+
"shape": [
|
577 |
+
2048
|
578 |
+
],
|
579 |
+
"dtype": "float16",
|
580 |
+
"format": "f32-to-bf16",
|
581 |
+
"nbytes": 4096,
|
582 |
+
"byteOffset": 8388608
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"name": "model.layers.14.mlp.down_proj.weight",
|
586 |
+
"shape": [
|
587 |
+
2048,
|
588 |
+
5632
|
589 |
+
],
|
590 |
+
"dtype": "float16",
|
591 |
+
"format": "f32-to-bf16",
|
592 |
+
"nbytes": 23068672,
|
593 |
+
"byteOffset": 8392704
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"name": "model.layers.14.post_attention_layernorm.weight",
|
597 |
+
"shape": [
|
598 |
+
2048
|
599 |
+
],
|
600 |
+
"dtype": "float16",
|
601 |
+
"format": "f32-to-bf16",
|
602 |
+
"nbytes": 4096,
|
603 |
+
"byteOffset": 31461376
|
604 |
+
}
|
605 |
+
],
|
606 |
+
"md5sum": "e5a3358dbf6572e5f29eb0574a2710f8"
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"dataPath": "params_shard_19.bin",
|
610 |
+
"format": "raw-shard",
|
611 |
+
"nbytes": 23068672,
|
612 |
+
"records": [
|
613 |
+
{
|
614 |
+
"name": "model.layers.15.mlp.down_proj.weight",
|
615 |
+
"shape": [
|
616 |
+
2048,
|
617 |
+
5632
|
618 |
+
],
|
619 |
+
"dtype": "float16",
|
620 |
+
"format": "f32-to-bf16",
|
621 |
+
"nbytes": 23068672,
|
622 |
+
"byteOffset": 0
|
623 |
+
}
|
624 |
+
],
|
625 |
+
"md5sum": "3693cba59637b5c149ea328e75d65f10"
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"dataPath": "params_shard_20.bin",
|
629 |
+
"format": "raw-shard",
|
630 |
+
"nbytes": 46137344,
|
631 |
+
"records": [
|
632 |
+
{
|
633 |
+
"name": "model.layers.15.mlp.gate_up_proj.weight",
|
634 |
+
"shape": [
|
635 |
+
11264,
|
636 |
+
2048
|
637 |
+
],
|
638 |
+
"dtype": "float16",
|
639 |
+
"format": "f32-to-bf16",
|
640 |
+
"nbytes": 46137344,
|
641 |
+
"byteOffset": 0
|
642 |
+
}
|
643 |
+
],
|
644 |
+
"md5sum": "f9b6be0eef3c969c9399ec2c19a86812"
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"dataPath": "params_shard_21.bin",
|
648 |
+
"format": "raw-shard",
|
649 |
+
"nbytes": 29368320,
|
650 |
+
"records": [
|
651 |
+
{
|
652 |
+
"name": "model.layers.14.self_attn.qkv_proj.weight",
|
653 |
+
"shape": [
|
654 |
+
2560,
|
655 |
+
2048
|
656 |
+
],
|
657 |
+
"dtype": "float16",
|
658 |
+
"format": "f32-to-bf16",
|
659 |
+
"nbytes": 10485760,
|
660 |
+
"byteOffset": 0
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"name": "model.layers.14.self_attn.o_proj.weight",
|
664 |
+
"shape": [
|
665 |
+
2048,
|
666 |
+
2048
|
667 |
+
],
|
668 |
+
"dtype": "float16",
|
669 |
+
"format": "f32-to-bf16",
|
670 |
+
"nbytes": 8388608,
|
671 |
+
"byteOffset": 10485760
|
672 |
+
},
|
673 |
+
{
|
674 |
+
"name": "model.layers.15.input_layernorm.weight",
|
675 |
+
"shape": [
|
676 |
+
2048
|
677 |
+
],
|
678 |
+
"dtype": "float16",
|
679 |
+
"format": "f32-to-bf16",
|
680 |
+
"nbytes": 4096,
|
681 |
+
"byteOffset": 18874368
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"name": "model.layers.15.post_attention_layernorm.weight",
|
685 |
+
"shape": [
|
686 |
+
2048
|
687 |
+
],
|
688 |
+
"dtype": "float16",
|
689 |
+
"format": "f32-to-bf16",
|
690 |
+
"nbytes": 4096,
|
691 |
+
"byteOffset": 18878464
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"name": "model.layers.15.self_attn.qkv_proj.weight",
|
695 |
+
"shape": [
|
696 |
+
2560,
|
697 |
+
2048
|
698 |
+
],
|
699 |
+
"dtype": "float16",
|
700 |
+
"format": "f32-to-bf16",
|
701 |
+
"nbytes": 10485760,
|
702 |
+
"byteOffset": 18882560
|
703 |
+
}
|
704 |
+
],
|
705 |
+
"md5sum": "3bda08ef56d03fa0935cda8e62f577e8"
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"dataPath": "params_shard_22.bin",
|
709 |
+
"format": "raw-shard",
|
710 |
+
"nbytes": 46137344,
|
711 |
+
"records": [
|
712 |
+
{
|
713 |
+
"name": "model.layers.16.mlp.gate_up_proj.weight",
|
714 |
+
"shape": [
|
715 |
+
11264,
|
716 |
+
2048
|
717 |
+
],
|
718 |
+
"dtype": "float16",
|
719 |
+
"format": "f32-to-bf16",
|
720 |
+
"nbytes": 46137344,
|
721 |
+
"byteOffset": 0
|
722 |
+
}
|
723 |
+
],
|
724 |
+
"md5sum": "5f214b1f00df2168b293c54b93f698da"
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"dataPath": "params_shard_23.bin",
|
728 |
+
"format": "raw-shard",
|
729 |
+
"nbytes": 31465472,
|
730 |
+
"records": [
|
731 |
+
{
|
732 |
+
"name": "model.layers.15.self_attn.o_proj.weight",
|
733 |
+
"shape": [
|
734 |
+
2048,
|
735 |
+
2048
|
736 |
+
],
|
737 |
+
"dtype": "float16",
|
738 |
+
"format": "f32-to-bf16",
|
739 |
+
"nbytes": 8388608,
|
740 |
+
"byteOffset": 0
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"name": "model.layers.16.input_layernorm.weight",
|
744 |
+
"shape": [
|
745 |
+
2048
|
746 |
+
],
|
747 |
+
"dtype": "float16",
|
748 |
+
"format": "f32-to-bf16",
|
749 |
+
"nbytes": 4096,
|
750 |
+
"byteOffset": 8388608
|
751 |
+
},
|
752 |
+
{
|
753 |
+
"name": "model.layers.16.mlp.down_proj.weight",
|
754 |
+
"shape": [
|
755 |
+
2048,
|
756 |
+
5632
|
757 |
+
],
|
758 |
+
"dtype": "float16",
|
759 |
+
"format": "f32-to-bf16",
|
760 |
+
"nbytes": 23068672,
|
761 |
+
"byteOffset": 8392704
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"name": "model.layers.16.post_attention_layernorm.weight",
|
765 |
+
"shape": [
|
766 |
+
2048
|
767 |
+
],
|
768 |
+
"dtype": "float16",
|
769 |
+
"format": "f32-to-bf16",
|
770 |
+
"nbytes": 4096,
|
771 |
+
"byteOffset": 31461376
|
772 |
+
}
|
773 |
+
],
|
774 |
+
"md5sum": "02f1b4551f1f43ea9a9d3eaef08949c7"
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"dataPath": "params_shard_24.bin",
|
778 |
+
"format": "raw-shard",
|
779 |
+
"nbytes": 23068672,
|
780 |
+
"records": [
|
781 |
+
{
|
782 |
+
"name": "model.layers.17.mlp.down_proj.weight",
|
783 |
+
"shape": [
|
784 |
+
2048,
|
785 |
+
5632
|
786 |
+
],
|
787 |
+
"dtype": "float16",
|
788 |
+
"format": "f32-to-bf16",
|
789 |
+
"nbytes": 23068672,
|
790 |
+
"byteOffset": 0
|
791 |
+
}
|
792 |
+
],
|
793 |
+
"md5sum": "91a33e4116fcaf5f483a6af8a5c84d06"
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"dataPath": "params_shard_25.bin",
|
797 |
+
"format": "raw-shard",
|
798 |
+
"nbytes": 46137344,
|
799 |
+
"records": [
|
800 |
+
{
|
801 |
+
"name": "model.layers.17.mlp.gate_up_proj.weight",
|
802 |
+
"shape": [
|
803 |
+
11264,
|
804 |
+
2048
|
805 |
+
],
|
806 |
+
"dtype": "float16",
|
807 |
+
"format": "f32-to-bf16",
|
808 |
+
"nbytes": 46137344,
|
809 |
+
"byteOffset": 0
|
810 |
+
}
|
811 |
+
],
|
812 |
+
"md5sum": "d9a62f0ab43e06c6ada7e8f33c0b2e9b"
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"dataPath": "params_shard_26.bin",
|
816 |
+
"format": "raw-shard",
|
817 |
+
"nbytes": 29368320,
|
818 |
+
"records": [
|
819 |
+
{
|
820 |
+
"name": "model.layers.16.self_attn.qkv_proj.weight",
|
821 |
+
"shape": [
|
822 |
+
2560,
|
823 |
+
2048
|
824 |
+
],
|
825 |
+
"dtype": "float16",
|
826 |
+
"format": "f32-to-bf16",
|
827 |
+
"nbytes": 10485760,
|
828 |
+
"byteOffset": 0
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"name": "model.layers.16.self_attn.o_proj.weight",
|
832 |
+
"shape": [
|
833 |
+
2048,
|
834 |
+
2048
|
835 |
+
],
|
836 |
+
"dtype": "float16",
|
837 |
+
"format": "f32-to-bf16",
|
838 |
+
"nbytes": 8388608,
|
839 |
+
"byteOffset": 10485760
|
840 |
+
},
|
841 |
+
{
|
842 |
+
"name": "model.layers.17.input_layernorm.weight",
|
843 |
+
"shape": [
|
844 |
+
2048
|
845 |
+
],
|
846 |
+
"dtype": "float16",
|
847 |
+
"format": "f32-to-bf16",
|
848 |
+
"nbytes": 4096,
|
849 |
+
"byteOffset": 18874368
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"name": "model.layers.17.post_attention_layernorm.weight",
|
853 |
+
"shape": [
|
854 |
+
2048
|
855 |
+
],
|
856 |
+
"dtype": "float16",
|
857 |
+
"format": "f32-to-bf16",
|
858 |
+
"nbytes": 4096,
|
859 |
+
"byteOffset": 18878464
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"name": "model.layers.17.self_attn.qkv_proj.weight",
|
863 |
+
"shape": [
|
864 |
+
2560,
|
865 |
+
2048
|
866 |
+
],
|
867 |
+
"dtype": "float16",
|
868 |
+
"format": "f32-to-bf16",
|
869 |
+
"nbytes": 10485760,
|
870 |
+
"byteOffset": 18882560
|
871 |
+
}
|
872 |
+
],
|
873 |
+
"md5sum": "062d11c5e83c3ab3f29441999dff582a"
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"dataPath": "params_shard_27.bin",
|
877 |
+
"format": "raw-shard",
|
878 |
+
"nbytes": 46137344,
|
879 |
+
"records": [
|
880 |
+
{
|
881 |
+
"name": "model.layers.18.mlp.gate_up_proj.weight",
|
882 |
+
"shape": [
|
883 |
+
11264,
|
884 |
+
2048
|
885 |
+
],
|
886 |
+
"dtype": "float16",
|
887 |
+
"format": "f32-to-bf16",
|
888 |
+
"nbytes": 46137344,
|
889 |
+
"byteOffset": 0
|
890 |
+
}
|
891 |
+
],
|
892 |
+
"md5sum": "12fb5e1c494c84a7956d41a25cdd1d7e"
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"dataPath": "params_shard_28.bin",
|
896 |
+
"format": "raw-shard",
|
897 |
+
"nbytes": 31465472,
|
898 |
+
"records": [
|
899 |
+
{
|
900 |
+
"name": "model.layers.17.self_attn.o_proj.weight",
|
901 |
+
"shape": [
|
902 |
+
2048,
|
903 |
+
2048
|
904 |
+
],
|
905 |
+
"dtype": "float16",
|
906 |
+
"format": "f32-to-bf16",
|
907 |
+
"nbytes": 8388608,
|
908 |
+
"byteOffset": 0
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"name": "model.layers.18.input_layernorm.weight",
|
912 |
+
"shape": [
|
913 |
+
2048
|
914 |
+
],
|
915 |
+
"dtype": "float16",
|
916 |
+
"format": "f32-to-bf16",
|
917 |
+
"nbytes": 4096,
|
918 |
+
"byteOffset": 8388608
|
919 |
+
},
|
920 |
+
{
|
921 |
+
"name": "model.layers.18.mlp.down_proj.weight",
|
922 |
+
"shape": [
|
923 |
+
2048,
|
924 |
+
5632
|
925 |
+
],
|
926 |
+
"dtype": "float16",
|
927 |
+
"format": "f32-to-bf16",
|
928 |
+
"nbytes": 23068672,
|
929 |
+
"byteOffset": 8392704
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"name": "model.layers.18.post_attention_layernorm.weight",
|
933 |
+
"shape": [
|
934 |
+
2048
|
935 |
+
],
|
936 |
+
"dtype": "float16",
|
937 |
+
"format": "f32-to-bf16",
|
938 |
+
"nbytes": 4096,
|
939 |
+
"byteOffset": 31461376
|
940 |
+
}
|
941 |
+
],
|
942 |
+
"md5sum": "7c7cb40e5739912436dffe8f5415a653"
|
943 |
+
},
|
944 |
+
{
|
945 |
+
"dataPath": "params_shard_29.bin",
|
946 |
+
"format": "raw-shard",
|
947 |
+
"nbytes": 23068672,
|
948 |
+
"records": [
|
949 |
+
{
|
950 |
+
"name": "model.layers.19.mlp.down_proj.weight",
|
951 |
+
"shape": [
|
952 |
+
2048,
|
953 |
+
5632
|
954 |
+
],
|
955 |
+
"dtype": "float16",
|
956 |
+
"format": "f32-to-bf16",
|
957 |
+
"nbytes": 23068672,
|
958 |
+
"byteOffset": 0
|
959 |
+
}
|
960 |
+
],
|
961 |
+
"md5sum": "e19364880512f131126e7385d9c32eac"
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"dataPath": "params_shard_30.bin",
|
965 |
+
"format": "raw-shard",
|
966 |
+
"nbytes": 46137344,
|
967 |
+
"records": [
|
968 |
+
{
|
969 |
+
"name": "model.layers.19.mlp.gate_up_proj.weight",
|
970 |
+
"shape": [
|
971 |
+
11264,
|
972 |
+
2048
|
973 |
+
],
|
974 |
+
"dtype": "float16",
|
975 |
+
"format": "f32-to-bf16",
|
976 |
+
"nbytes": 46137344,
|
977 |
+
"byteOffset": 0
|
978 |
+
}
|
979 |
+
],
|
980 |
+
"md5sum": "64f981313696f188e4bd7478ef039125"
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"dataPath": "params_shard_31.bin",
|
984 |
+
"format": "raw-shard",
|
985 |
+
"nbytes": 29368320,
|
986 |
+
"records": [
|
987 |
+
{
|
988 |
+
"name": "model.layers.18.self_attn.qkv_proj.weight",
|
989 |
+
"shape": [
|
990 |
+
2560,
|
991 |
+
2048
|
992 |
+
],
|
993 |
+
"dtype": "float16",
|
994 |
+
"format": "f32-to-bf16",
|
995 |
+
"nbytes": 10485760,
|
996 |
+
"byteOffset": 0
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"name": "model.layers.18.self_attn.o_proj.weight",
|
1000 |
+
"shape": [
|
1001 |
+
2048,
|
1002 |
+
2048
|
1003 |
+
],
|
1004 |
+
"dtype": "float16",
|
1005 |
+
"format": "f32-to-bf16",
|
1006 |
+
"nbytes": 8388608,
|
1007 |
+
"byteOffset": 10485760
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"name": "model.layers.19.input_layernorm.weight",
|
1011 |
+
"shape": [
|
1012 |
+
2048
|
1013 |
+
],
|
1014 |
+
"dtype": "float16",
|
1015 |
+
"format": "f32-to-bf16",
|
1016 |
+
"nbytes": 4096,
|
1017 |
+
"byteOffset": 18874368
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"name": "model.layers.19.post_attention_layernorm.weight",
|
1021 |
+
"shape": [
|
1022 |
+
2048
|
1023 |
+
],
|
1024 |
+
"dtype": "float16",
|
1025 |
+
"format": "f32-to-bf16",
|
1026 |
+
"nbytes": 4096,
|
1027 |
+
"byteOffset": 18878464
|
1028 |
+
},
|
1029 |
+
{
|
1030 |
+
"name": "model.layers.19.self_attn.qkv_proj.weight",
|
1031 |
+
"shape": [
|
1032 |
+
2560,
|
1033 |
+
2048
|
1034 |
+
],
|
1035 |
+
"dtype": "float16",
|
1036 |
+
"format": "f32-to-bf16",
|
1037 |
+
"nbytes": 10485760,
|
1038 |
+
"byteOffset": 18882560
|
1039 |
+
}
|
1040 |
+
],
|
1041 |
+
"md5sum": "432c244c8ec1a184ad618484d7cf897b"
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"dataPath": "params_shard_32.bin",
|
1045 |
+
"format": "raw-shard",
|
1046 |
+
"nbytes": 46137344,
|
1047 |
+
"records": [
|
1048 |
+
{
|
1049 |
+
"name": "model.layers.2.mlp.gate_up_proj.weight",
|
1050 |
+
"shape": [
|
1051 |
+
11264,
|
1052 |
+
2048
|
1053 |
+
],
|
1054 |
+
"dtype": "float16",
|
1055 |
+
"format": "f32-to-bf16",
|
1056 |
+
"nbytes": 46137344,
|
1057 |
+
"byteOffset": 0
|
1058 |
+
}
|
1059 |
+
],
|
1060 |
+
"md5sum": "63271c6a96f05bc97bf159176e6d5589"
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"dataPath": "params_shard_33.bin",
|
1064 |
+
"format": "raw-shard",
|
1065 |
+
"nbytes": 31465472,
|
1066 |
+
"records": [
|
1067 |
+
{
|
1068 |
+
"name": "model.layers.19.self_attn.o_proj.weight",
|
1069 |
+
"shape": [
|
1070 |
+
2048,
|
1071 |
+
2048
|
1072 |
+
],
|
1073 |
+
"dtype": "float16",
|
1074 |
+
"format": "f32-to-bf16",
|
1075 |
+
"nbytes": 8388608,
|
1076 |
+
"byteOffset": 0
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"name": "model.layers.2.input_layernorm.weight",
|
1080 |
+
"shape": [
|
1081 |
+
2048
|
1082 |
+
],
|
1083 |
+
"dtype": "float16",
|
1084 |
+
"format": "f32-to-bf16",
|
1085 |
+
"nbytes": 4096,
|
1086 |
+
"byteOffset": 8388608
|
1087 |
+
},
|
1088 |
+
{
|
1089 |
+
"name": "model.layers.2.mlp.down_proj.weight",
|
1090 |
+
"shape": [
|
1091 |
+
2048,
|
1092 |
+
5632
|
1093 |
+
],
|
1094 |
+
"dtype": "float16",
|
1095 |
+
"format": "f32-to-bf16",
|
1096 |
+
"nbytes": 23068672,
|
1097 |
+
"byteOffset": 8392704
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"name": "model.layers.2.post_attention_layernorm.weight",
|
1101 |
+
"shape": [
|
1102 |
+
2048
|
1103 |
+
],
|
1104 |
+
"dtype": "float16",
|
1105 |
+
"format": "f32-to-bf16",
|
1106 |
+
"nbytes": 4096,
|
1107 |
+
"byteOffset": 31461376
|
1108 |
+
}
|
1109 |
+
],
|
1110 |
+
"md5sum": "cadfaa50f214b92d0c35d239543c61e4"
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"dataPath": "params_shard_34.bin",
|
1114 |
+
"format": "raw-shard",
|
1115 |
+
"nbytes": 23068672,
|
1116 |
+
"records": [
|
1117 |
+
{
|
1118 |
+
"name": "model.layers.20.mlp.down_proj.weight",
|
1119 |
+
"shape": [
|
1120 |
+
2048,
|
1121 |
+
5632
|
1122 |
+
],
|
1123 |
+
"dtype": "float16",
|
1124 |
+
"format": "f32-to-bf16",
|
1125 |
+
"nbytes": 23068672,
|
1126 |
+
"byteOffset": 0
|
1127 |
+
}
|
1128 |
+
],
|
1129 |
+
"md5sum": "33dc7e372670369500baae0a73e738e5"
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"dataPath": "params_shard_35.bin",
|
1133 |
+
"format": "raw-shard",
|
1134 |
+
"nbytes": 46137344,
|
1135 |
+
"records": [
|
1136 |
+
{
|
1137 |
+
"name": "model.layers.20.mlp.gate_up_proj.weight",
|
1138 |
+
"shape": [
|
1139 |
+
11264,
|
1140 |
+
2048
|
1141 |
+
],
|
1142 |
+
"dtype": "float16",
|
1143 |
+
"format": "f32-to-bf16",
|
1144 |
+
"nbytes": 46137344,
|
1145 |
+
"byteOffset": 0
|
1146 |
+
}
|
1147 |
+
],
|
1148 |
+
"md5sum": "9c2ed598e4412ee933e673ef0606d300"
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"dataPath": "params_shard_36.bin",
|
1152 |
+
"format": "raw-shard",
|
1153 |
+
"nbytes": 29368320,
|
1154 |
+
"records": [
|
1155 |
+
{
|
1156 |
+
"name": "model.layers.2.self_attn.qkv_proj.weight",
|
1157 |
+
"shape": [
|
1158 |
+
2560,
|
1159 |
+
2048
|
1160 |
+
],
|
1161 |
+
"dtype": "float16",
|
1162 |
+
"format": "f32-to-bf16",
|
1163 |
+
"nbytes": 10485760,
|
1164 |
+
"byteOffset": 0
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"name": "model.layers.2.self_attn.o_proj.weight",
|
1168 |
+
"shape": [
|
1169 |
+
2048,
|
1170 |
+
2048
|
1171 |
+
],
|
1172 |
+
"dtype": "float16",
|
1173 |
+
"format": "f32-to-bf16",
|
1174 |
+
"nbytes": 8388608,
|
1175 |
+
"byteOffset": 10485760
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"name": "model.layers.20.input_layernorm.weight",
|
1179 |
+
"shape": [
|
1180 |
+
2048
|
1181 |
+
],
|
1182 |
+
"dtype": "float16",
|
1183 |
+
"format": "f32-to-bf16",
|
1184 |
+
"nbytes": 4096,
|
1185 |
+
"byteOffset": 18874368
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"name": "model.layers.20.post_attention_layernorm.weight",
|
1189 |
+
"shape": [
|
1190 |
+
2048
|
1191 |
+
],
|
1192 |
+
"dtype": "float16",
|
1193 |
+
"format": "f32-to-bf16",
|
1194 |
+
"nbytes": 4096,
|
1195 |
+
"byteOffset": 18878464
|
1196 |
+
},
|
1197 |
+
{
|
1198 |
+
"name": "model.layers.20.self_attn.qkv_proj.weight",
|
1199 |
+
"shape": [
|
1200 |
+
2560,
|
1201 |
+
2048
|
1202 |
+
],
|
1203 |
+
"dtype": "float16",
|
1204 |
+
"format": "f32-to-bf16",
|
1205 |
+
"nbytes": 10485760,
|
1206 |
+
"byteOffset": 18882560
|
1207 |
+
}
|
1208 |
+
],
|
1209 |
+
"md5sum": "d2f3b396661e2381677d102eedf9fec2"
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"dataPath": "params_shard_37.bin",
|
1213 |
+
"format": "raw-shard",
|
1214 |
+
"nbytes": 46137344,
|
1215 |
+
"records": [
|
1216 |
+
{
|
1217 |
+
"name": "model.layers.21.mlp.gate_up_proj.weight",
|
1218 |
+
"shape": [
|
1219 |
+
11264,
|
1220 |
+
2048
|
1221 |
+
],
|
1222 |
+
"dtype": "float16",
|
1223 |
+
"format": "f32-to-bf16",
|
1224 |
+
"nbytes": 46137344,
|
1225 |
+
"byteOffset": 0
|
1226 |
+
}
|
1227 |
+
],
|
1228 |
+
"md5sum": "90560d68478e9aaf9ab18f7d565e2979"
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"dataPath": "params_shard_38.bin",
|
1232 |
+
"format": "raw-shard",
|
1233 |
+
"nbytes": 31465472,
|
1234 |
+
"records": [
|
1235 |
+
{
|
1236 |
+
"name": "model.layers.20.self_attn.o_proj.weight",
|
1237 |
+
"shape": [
|
1238 |
+
2048,
|
1239 |
+
2048
|
1240 |
+
],
|
1241 |
+
"dtype": "float16",
|
1242 |
+
"format": "f32-to-bf16",
|
1243 |
+
"nbytes": 8388608,
|
1244 |
+
"byteOffset": 0
|
1245 |
+
},
|
1246 |
+
{
|
1247 |
+
"name": "model.layers.21.input_layernorm.weight",
|
1248 |
+
"shape": [
|
1249 |
+
2048
|
1250 |
+
],
|
1251 |
+
"dtype": "float16",
|
1252 |
+
"format": "f32-to-bf16",
|
1253 |
+
"nbytes": 4096,
|
1254 |
+
"byteOffset": 8388608
|
1255 |
+
},
|
1256 |
+
{
|
1257 |
+
"name": "model.layers.21.mlp.down_proj.weight",
|
1258 |
+
"shape": [
|
1259 |
+
2048,
|
1260 |
+
5632
|
1261 |
+
],
|
1262 |
+
"dtype": "float16",
|
1263 |
+
"format": "f32-to-bf16",
|
1264 |
+
"nbytes": 23068672,
|
1265 |
+
"byteOffset": 8392704
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"name": "model.layers.21.post_attention_layernorm.weight",
|
1269 |
+
"shape": [
|
1270 |
+
2048
|
1271 |
+
],
|
1272 |
+
"dtype": "float16",
|
1273 |
+
"format": "f32-to-bf16",
|
1274 |
+
"nbytes": 4096,
|
1275 |
+
"byteOffset": 31461376
|
1276 |
+
}
|
1277 |
+
],
|
1278 |
+
"md5sum": "f7dad919d98f25f033bdb2f1e670213e"
|
1279 |
+
},
|
1280 |
+
{
|
1281 |
+
"dataPath": "params_shard_39.bin",
|
1282 |
+
"format": "raw-shard",
|
1283 |
+
"nbytes": 23068672,
|
1284 |
+
"records": [
|
1285 |
+
{
|
1286 |
+
"name": "model.layers.3.mlp.down_proj.weight",
|
1287 |
+
"shape": [
|
1288 |
+
2048,
|
1289 |
+
5632
|
1290 |
+
],
|
1291 |
+
"dtype": "float16",
|
1292 |
+
"format": "f32-to-bf16",
|
1293 |
+
"nbytes": 23068672,
|
1294 |
+
"byteOffset": 0
|
1295 |
+
}
|
1296 |
+
],
|
1297 |
+
"md5sum": "7058d133bf8c15defd0608f5cc39ecf5"
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"dataPath": "params_shard_40.bin",
|
1301 |
+
"format": "raw-shard",
|
1302 |
+
"nbytes": 46137344,
|
1303 |
+
"records": [
|
1304 |
+
{
|
1305 |
+
"name": "model.layers.3.mlp.gate_up_proj.weight",
|
1306 |
+
"shape": [
|
1307 |
+
11264,
|
1308 |
+
2048
|
1309 |
+
],
|
1310 |
+
"dtype": "float16",
|
1311 |
+
"format": "f32-to-bf16",
|
1312 |
+
"nbytes": 46137344,
|
1313 |
+
"byteOffset": 0
|
1314 |
+
}
|
1315 |
+
],
|
1316 |
+
"md5sum": "8c9470bf89d281643a4f7ecfbceded3b"
|
1317 |
+
},
|
1318 |
+
{
|
1319 |
+
"dataPath": "params_shard_41.bin",
|
1320 |
+
"format": "raw-shard",
|
1321 |
+
"nbytes": 29368320,
|
1322 |
+
"records": [
|
1323 |
+
{
|
1324 |
+
"name": "model.layers.21.self_attn.qkv_proj.weight",
|
1325 |
+
"shape": [
|
1326 |
+
2560,
|
1327 |
+
2048
|
1328 |
+
],
|
1329 |
+
"dtype": "float16",
|
1330 |
+
"format": "f32-to-bf16",
|
1331 |
+
"nbytes": 10485760,
|
1332 |
+
"byteOffset": 0
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"name": "model.layers.21.self_attn.o_proj.weight",
|
1336 |
+
"shape": [
|
1337 |
+
2048,
|
1338 |
+
2048
|
1339 |
+
],
|
1340 |
+
"dtype": "float16",
|
1341 |
+
"format": "f32-to-bf16",
|
1342 |
+
"nbytes": 8388608,
|
1343 |
+
"byteOffset": 10485760
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"name": "model.layers.3.input_layernorm.weight",
|
1347 |
+
"shape": [
|
1348 |
+
2048
|
1349 |
+
],
|
1350 |
+
"dtype": "float16",
|
1351 |
+
"format": "f32-to-bf16",
|
1352 |
+
"nbytes": 4096,
|
1353 |
+
"byteOffset": 18874368
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"name": "model.layers.3.post_attention_layernorm.weight",
|
1357 |
+
"shape": [
|
1358 |
+
2048
|
1359 |
+
],
|
1360 |
+
"dtype": "float16",
|
1361 |
+
"format": "f32-to-bf16",
|
1362 |
+
"nbytes": 4096,
|
1363 |
+
"byteOffset": 18878464
|
1364 |
+
},
|
1365 |
+
{
|
1366 |
+
"name": "model.layers.3.self_attn.qkv_proj.weight",
|
1367 |
+
"shape": [
|
1368 |
+
2560,
|
1369 |
+
2048
|
1370 |
+
],
|
1371 |
+
"dtype": "float16",
|
1372 |
+
"format": "f32-to-bf16",
|
1373 |
+
"nbytes": 10485760,
|
1374 |
+
"byteOffset": 18882560
|
1375 |
+
}
|
1376 |
+
],
|
1377 |
+
"md5sum": "be1adb2bbb2b85b38ad3811d55eee72a"
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"dataPath": "params_shard_42.bin",
|
1381 |
+
"format": "raw-shard",
|
1382 |
+
"nbytes": 46137344,
|
1383 |
+
"records": [
|
1384 |
+
{
|
1385 |
+
"name": "model.layers.4.mlp.gate_up_proj.weight",
|
1386 |
+
"shape": [
|
1387 |
+
11264,
|
1388 |
+
2048
|
1389 |
+
],
|
1390 |
+
"dtype": "float16",
|
1391 |
+
"format": "f32-to-bf16",
|
1392 |
+
"nbytes": 46137344,
|
1393 |
+
"byteOffset": 0
|
1394 |
+
}
|
1395 |
+
],
|
1396 |
+
"md5sum": "2a986af683615d0b0b832ccdd1c9d3d0"
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"dataPath": "params_shard_43.bin",
|
1400 |
+
"format": "raw-shard",
|
1401 |
+
"nbytes": 31465472,
|
1402 |
+
"records": [
|
1403 |
+
{
|
1404 |
+
"name": "model.layers.3.self_attn.o_proj.weight",
|
1405 |
+
"shape": [
|
1406 |
+
2048,
|
1407 |
+
2048
|
1408 |
+
],
|
1409 |
+
"dtype": "float16",
|
1410 |
+
"format": "f32-to-bf16",
|
1411 |
+
"nbytes": 8388608,
|
1412 |
+
"byteOffset": 0
|
1413 |
+
},
|
1414 |
+
{
|
1415 |
+
"name": "model.layers.4.input_layernorm.weight",
|
1416 |
+
"shape": [
|
1417 |
+
2048
|
1418 |
+
],
|
1419 |
+
"dtype": "float16",
|
1420 |
+
"format": "f32-to-bf16",
|
1421 |
+
"nbytes": 4096,
|
1422 |
+
"byteOffset": 8388608
|
1423 |
+
},
|
1424 |
+
{
|
1425 |
+
"name": "model.layers.4.mlp.down_proj.weight",
|
1426 |
+
"shape": [
|
1427 |
+
2048,
|
1428 |
+
5632
|
1429 |
+
],
|
1430 |
+
"dtype": "float16",
|
1431 |
+
"format": "f32-to-bf16",
|
1432 |
+
"nbytes": 23068672,
|
1433 |
+
"byteOffset": 8392704
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"name": "model.layers.4.post_attention_layernorm.weight",
|
1437 |
+
"shape": [
|
1438 |
+
2048
|
1439 |
+
],
|
1440 |
+
"dtype": "float16",
|
1441 |
+
"format": "f32-to-bf16",
|
1442 |
+
"nbytes": 4096,
|
1443 |
+
"byteOffset": 31461376
|
1444 |
+
}
|
1445 |
+
],
|
1446 |
+
"md5sum": "0630623a24b0ed117b9d082a40400a74"
|
1447 |
+
},
|
1448 |
+
{
|
1449 |
+
"dataPath": "params_shard_44.bin",
|
1450 |
+
"format": "raw-shard",
|
1451 |
+
"nbytes": 23068672,
|
1452 |
+
"records": [
|
1453 |
+
{
|
1454 |
+
"name": "model.layers.5.mlp.down_proj.weight",
|
1455 |
+
"shape": [
|
1456 |
+
2048,
|
1457 |
+
5632
|
1458 |
+
],
|
1459 |
+
"dtype": "float16",
|
1460 |
+
"format": "f32-to-bf16",
|
1461 |
+
"nbytes": 23068672,
|
1462 |
+
"byteOffset": 0
|
1463 |
+
}
|
1464 |
+
],
|
1465 |
+
"md5sum": "8cb5908d2c193dbb86a4af843ddbf324"
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"dataPath": "params_shard_45.bin",
|
1469 |
+
"format": "raw-shard",
|
1470 |
+
"nbytes": 46137344,
|
1471 |
+
"records": [
|
1472 |
+
{
|
1473 |
+
"name": "model.layers.5.mlp.gate_up_proj.weight",
|
1474 |
+
"shape": [
|
1475 |
+
11264,
|
1476 |
+
2048
|
1477 |
+
],
|
1478 |
+
"dtype": "float16",
|
1479 |
+
"format": "f32-to-bf16",
|
1480 |
+
"nbytes": 46137344,
|
1481 |
+
"byteOffset": 0
|
1482 |
+
}
|
1483 |
+
],
|
1484 |
+
"md5sum": "f181953e69d8fd705c4e4f10ccf3001f"
|
1485 |
+
},
|
1486 |
+
{
|
1487 |
+
"dataPath": "params_shard_46.bin",
|
1488 |
+
"format": "raw-shard",
|
1489 |
+
"nbytes": 29368320,
|
1490 |
+
"records": [
|
1491 |
+
{
|
1492 |
+
"name": "model.layers.4.self_attn.qkv_proj.weight",
|
1493 |
+
"shape": [
|
1494 |
+
2560,
|
1495 |
+
2048
|
1496 |
+
],
|
1497 |
+
"dtype": "float16",
|
1498 |
+
"format": "f32-to-bf16",
|
1499 |
+
"nbytes": 10485760,
|
1500 |
+
"byteOffset": 0
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"name": "model.layers.4.self_attn.o_proj.weight",
|
1504 |
+
"shape": [
|
1505 |
+
2048,
|
1506 |
+
2048
|
1507 |
+
],
|
1508 |
+
"dtype": "float16",
|
1509 |
+
"format": "f32-to-bf16",
|
1510 |
+
"nbytes": 8388608,
|
1511 |
+
"byteOffset": 10485760
|
1512 |
+
},
|
1513 |
+
{
|
1514 |
+
"name": "model.layers.5.input_layernorm.weight",
|
1515 |
+
"shape": [
|
1516 |
+
2048
|
1517 |
+
],
|
1518 |
+
"dtype": "float16",
|
1519 |
+
"format": "f32-to-bf16",
|
1520 |
+
"nbytes": 4096,
|
1521 |
+
"byteOffset": 18874368
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"name": "model.layers.5.post_attention_layernorm.weight",
|
1525 |
+
"shape": [
|
1526 |
+
2048
|
1527 |
+
],
|
1528 |
+
"dtype": "float16",
|
1529 |
+
"format": "f32-to-bf16",
|
1530 |
+
"nbytes": 4096,
|
1531 |
+
"byteOffset": 18878464
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"name": "model.layers.5.self_attn.qkv_proj.weight",
|
1535 |
+
"shape": [
|
1536 |
+
2560,
|
1537 |
+
2048
|
1538 |
+
],
|
1539 |
+
"dtype": "float16",
|
1540 |
+
"format": "f32-to-bf16",
|
1541 |
+
"nbytes": 10485760,
|
1542 |
+
"byteOffset": 18882560
|
1543 |
+
}
|
1544 |
+
],
|
1545 |
+
"md5sum": "42d390f90d09a8f6b87cee627a11dde9"
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"dataPath": "params_shard_47.bin",
|
1549 |
+
"format": "raw-shard",
|
1550 |
+
"nbytes": 46137344,
|
1551 |
+
"records": [
|
1552 |
+
{
|
1553 |
+
"name": "model.layers.6.mlp.gate_up_proj.weight",
|
1554 |
+
"shape": [
|
1555 |
+
11264,
|
1556 |
+
2048
|
1557 |
+
],
|
1558 |
+
"dtype": "float16",
|
1559 |
+
"format": "f32-to-bf16",
|
1560 |
+
"nbytes": 46137344,
|
1561 |
+
"byteOffset": 0
|
1562 |
+
}
|
1563 |
+
],
|
1564 |
+
"md5sum": "e96c76d0d8a633cb1021918c02edb71d"
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"dataPath": "params_shard_48.bin",
|
1568 |
+
"format": "raw-shard",
|
1569 |
+
"nbytes": 31465472,
|
1570 |
+
"records": [
|
1571 |
+
{
|
1572 |
+
"name": "model.layers.5.self_attn.o_proj.weight",
|
1573 |
+
"shape": [
|
1574 |
+
2048,
|
1575 |
+
2048
|
1576 |
+
],
|
1577 |
+
"dtype": "float16",
|
1578 |
+
"format": "f32-to-bf16",
|
1579 |
+
"nbytes": 8388608,
|
1580 |
+
"byteOffset": 0
|
1581 |
+
},
|
1582 |
+
{
|
1583 |
+
"name": "model.layers.6.input_layernorm.weight",
|
1584 |
+
"shape": [
|
1585 |
+
2048
|
1586 |
+
],
|
1587 |
+
"dtype": "float16",
|
1588 |
+
"format": "f32-to-bf16",
|
1589 |
+
"nbytes": 4096,
|
1590 |
+
"byteOffset": 8388608
|
1591 |
+
},
|
1592 |
+
{
|
1593 |
+
"name": "model.layers.6.mlp.down_proj.weight",
|
1594 |
+
"shape": [
|
1595 |
+
2048,
|
1596 |
+
5632
|
1597 |
+
],
|
1598 |
+
"dtype": "float16",
|
1599 |
+
"format": "f32-to-bf16",
|
1600 |
+
"nbytes": 23068672,
|
1601 |
+
"byteOffset": 8392704
|
1602 |
+
},
|
1603 |
+
{
|
1604 |
+
"name": "model.layers.6.post_attention_layernorm.weight",
|
1605 |
+
"shape": [
|
1606 |
+
2048
|
1607 |
+
],
|
1608 |
+
"dtype": "float16",
|
1609 |
+
"format": "f32-to-bf16",
|
1610 |
+
"nbytes": 4096,
|
1611 |
+
"byteOffset": 31461376
|
1612 |
+
}
|
1613 |
+
],
|
1614 |
+
"md5sum": "b14c43e394cb826b709dd5a5ed0edf0a"
|
1615 |
+
},
|
1616 |
+
{
|
1617 |
+
"dataPath": "params_shard_49.bin",
|
1618 |
+
"format": "raw-shard",
|
1619 |
+
"nbytes": 23068672,
|
1620 |
+
"records": [
|
1621 |
+
{
|
1622 |
+
"name": "model.layers.7.mlp.down_proj.weight",
|
1623 |
+
"shape": [
|
1624 |
+
2048,
|
1625 |
+
5632
|
1626 |
+
],
|
1627 |
+
"dtype": "float16",
|
1628 |
+
"format": "f32-to-bf16",
|
1629 |
+
"nbytes": 23068672,
|
1630 |
+
"byteOffset": 0
|
1631 |
+
}
|
1632 |
+
],
|
1633 |
+
"md5sum": "9a49c18e3ea67739ec061eba259675ec"
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"dataPath": "params_shard_50.bin",
|
1637 |
+
"format": "raw-shard",
|
1638 |
+
"nbytes": 46137344,
|
1639 |
+
"records": [
|
1640 |
+
{
|
1641 |
+
"name": "model.layers.7.mlp.gate_up_proj.weight",
|
1642 |
+
"shape": [
|
1643 |
+
11264,
|
1644 |
+
2048
|
1645 |
+
],
|
1646 |
+
"dtype": "float16",
|
1647 |
+
"format": "f32-to-bf16",
|
1648 |
+
"nbytes": 46137344,
|
1649 |
+
"byteOffset": 0
|
1650 |
+
}
|
1651 |
+
],
|
1652 |
+
"md5sum": "fb02a48b192522544f1ecdbedd6c504e"
|
1653 |
+
},
|
1654 |
+
{
|
1655 |
+
"dataPath": "params_shard_51.bin",
|
1656 |
+
"format": "raw-shard",
|
1657 |
+
"nbytes": 29368320,
|
1658 |
+
"records": [
|
1659 |
+
{
|
1660 |
+
"name": "model.layers.6.self_attn.qkv_proj.weight",
|
1661 |
+
"shape": [
|
1662 |
+
2560,
|
1663 |
+
2048
|
1664 |
+
],
|
1665 |
+
"dtype": "float16",
|
1666 |
+
"format": "f32-to-bf16",
|
1667 |
+
"nbytes": 10485760,
|
1668 |
+
"byteOffset": 0
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"name": "model.layers.6.self_attn.o_proj.weight",
|
1672 |
+
"shape": [
|
1673 |
+
2048,
|
1674 |
+
2048
|
1675 |
+
],
|
1676 |
+
"dtype": "float16",
|
1677 |
+
"format": "f32-to-bf16",
|
1678 |
+
"nbytes": 8388608,
|
1679 |
+
"byteOffset": 10485760
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"name": "model.layers.7.input_layernorm.weight",
|
1683 |
+
"shape": [
|
1684 |
+
2048
|
1685 |
+
],
|
1686 |
+
"dtype": "float16",
|
1687 |
+
"format": "f32-to-bf16",
|
1688 |
+
"nbytes": 4096,
|
1689 |
+
"byteOffset": 18874368
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"name": "model.layers.7.post_attention_layernorm.weight",
|
1693 |
+
"shape": [
|
1694 |
+
2048
|
1695 |
+
],
|
1696 |
+
"dtype": "float16",
|
1697 |
+
"format": "f32-to-bf16",
|
1698 |
+
"nbytes": 4096,
|
1699 |
+
"byteOffset": 18878464
|
1700 |
+
},
|
1701 |
+
{
|
1702 |
+
"name": "model.layers.7.self_attn.qkv_proj.weight",
|
1703 |
+
"shape": [
|
1704 |
+
2560,
|
1705 |
+
2048
|
1706 |
+
],
|
1707 |
+
"dtype": "float16",
|
1708 |
+
"format": "f32-to-bf16",
|
1709 |
+
"nbytes": 10485760,
|
1710 |
+
"byteOffset": 18882560
|
1711 |
+
}
|
1712 |
+
],
|
1713 |
+
"md5sum": "354728bb842783df3121b3dd3c74be00"
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"dataPath": "params_shard_52.bin",
|
1717 |
+
"format": "raw-shard",
|
1718 |
+
"nbytes": 46137344,
|
1719 |
+
"records": [
|
1720 |
+
{
|
1721 |
+
"name": "model.layers.8.mlp.gate_up_proj.weight",
|
1722 |
+
"shape": [
|
1723 |
+
11264,
|
1724 |
+
2048
|
1725 |
+
],
|
1726 |
+
"dtype": "float16",
|
1727 |
+
"format": "f32-to-bf16",
|
1728 |
+
"nbytes": 46137344,
|
1729 |
+
"byteOffset": 0
|
1730 |
+
}
|
1731 |
+
],
|
1732 |
+
"md5sum": "9b3b2574f33b956f3d048433cc527dfc"
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"dataPath": "params_shard_53.bin",
|
1736 |
+
"format": "raw-shard",
|
1737 |
+
"nbytes": 31465472,
|
1738 |
+
"records": [
|
1739 |
+
{
|
1740 |
+
"name": "model.layers.7.self_attn.o_proj.weight",
|
1741 |
+
"shape": [
|
1742 |
+
2048,
|
1743 |
+
2048
|
1744 |
+
],
|
1745 |
+
"dtype": "float16",
|
1746 |
+
"format": "f32-to-bf16",
|
1747 |
+
"nbytes": 8388608,
|
1748 |
+
"byteOffset": 0
|
1749 |
+
},
|
1750 |
+
{
|
1751 |
+
"name": "model.layers.8.input_layernorm.weight",
|
1752 |
+
"shape": [
|
1753 |
+
2048
|
1754 |
+
],
|
1755 |
+
"dtype": "float16",
|
1756 |
+
"format": "f32-to-bf16",
|
1757 |
+
"nbytes": 4096,
|
1758 |
+
"byteOffset": 8388608
|
1759 |
+
},
|
1760 |
+
{
|
1761 |
+
"name": "model.layers.8.mlp.down_proj.weight",
|
1762 |
+
"shape": [
|
1763 |
+
2048,
|
1764 |
+
5632
|
1765 |
+
],
|
1766 |
+
"dtype": "float16",
|
1767 |
+
"format": "f32-to-bf16",
|
1768 |
+
"nbytes": 23068672,
|
1769 |
+
"byteOffset": 8392704
|
1770 |
+
},
|
1771 |
+
{
|
1772 |
+
"name": "model.layers.8.post_attention_layernorm.weight",
|
1773 |
+
"shape": [
|
1774 |
+
2048
|
1775 |
+
],
|
1776 |
+
"dtype": "float16",
|
1777 |
+
"format": "f32-to-bf16",
|
1778 |
+
"nbytes": 4096,
|
1779 |
+
"byteOffset": 31461376
|
1780 |
+
}
|
1781 |
+
],
|
1782 |
+
"md5sum": "d7766f4b6cf1ec4a102d3a8b1a512ab5"
|
1783 |
+
},
|
1784 |
+
{
|
1785 |
+
"dataPath": "params_shard_54.bin",
|
1786 |
+
"format": "raw-shard",
|
1787 |
+
"nbytes": 23068672,
|
1788 |
+
"records": [
|
1789 |
+
{
|
1790 |
+
"name": "model.layers.9.mlp.down_proj.weight",
|
1791 |
+
"shape": [
|
1792 |
+
2048,
|
1793 |
+
5632
|
1794 |
+
],
|
1795 |
+
"dtype": "float16",
|
1796 |
+
"format": "f32-to-bf16",
|
1797 |
+
"nbytes": 23068672,
|
1798 |
+
"byteOffset": 0
|
1799 |
+
}
|
1800 |
+
],
|
1801 |
+
"md5sum": "d8486986a2147c55770851dd04cf64bc"
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"dataPath": "params_shard_55.bin",
|
1805 |
+
"format": "raw-shard",
|
1806 |
+
"nbytes": 46137344,
|
1807 |
+
"records": [
|
1808 |
+
{
|
1809 |
+
"name": "model.layers.9.mlp.gate_up_proj.weight",
|
1810 |
+
"shape": [
|
1811 |
+
11264,
|
1812 |
+
2048
|
1813 |
+
],
|
1814 |
+
"dtype": "float16",
|
1815 |
+
"format": "f32-to-bf16",
|
1816 |
+
"nbytes": 46137344,
|
1817 |
+
"byteOffset": 0
|
1818 |
+
}
|
1819 |
+
],
|
1820 |
+
"md5sum": "f0cbb90d4428b9815210b55ae2e12267"
|
1821 |
+
},
|
1822 |
+
{
|
1823 |
+
"dataPath": "params_shard_56.bin",
|
1824 |
+
"format": "raw-shard",
|
1825 |
+
"nbytes": 29368320,
|
1826 |
+
"records": [
|
1827 |
+
{
|
1828 |
+
"name": "model.layers.8.self_attn.qkv_proj.weight",
|
1829 |
+
"shape": [
|
1830 |
+
2560,
|
1831 |
+
2048
|
1832 |
+
],
|
1833 |
+
"dtype": "float16",
|
1834 |
+
"format": "f32-to-bf16",
|
1835 |
+
"nbytes": 10485760,
|
1836 |
+
"byteOffset": 0
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"name": "model.layers.8.self_attn.o_proj.weight",
|
1840 |
+
"shape": [
|
1841 |
+
2048,
|
1842 |
+
2048
|
1843 |
+
],
|
1844 |
+
"dtype": "float16",
|
1845 |
+
"format": "f32-to-bf16",
|
1846 |
+
"nbytes": 8388608,
|
1847 |
+
"byteOffset": 10485760
|
1848 |
+
},
|
1849 |
+
{
|
1850 |
+
"name": "model.layers.9.input_layernorm.weight",
|
1851 |
+
"shape": [
|
1852 |
+
2048
|
1853 |
+
],
|
1854 |
+
"dtype": "float16",
|
1855 |
+
"format": "f32-to-bf16",
|
1856 |
+
"nbytes": 4096,
|
1857 |
+
"byteOffset": 18874368
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"name": "model.layers.9.post_attention_layernorm.weight",
|
1861 |
+
"shape": [
|
1862 |
+
2048
|
1863 |
+
],
|
1864 |
+
"dtype": "float16",
|
1865 |
+
"format": "f32-to-bf16",
|
1866 |
+
"nbytes": 4096,
|
1867 |
+
"byteOffset": 18878464
|
1868 |
+
},
|
1869 |
+
{
|
1870 |
+
"name": "model.layers.9.self_attn.qkv_proj.weight",
|
1871 |
+
"shape": [
|
1872 |
+
2560,
|
1873 |
+
2048
|
1874 |
+
],
|
1875 |
+
"dtype": "float16",
|
1876 |
+
"format": "f32-to-bf16",
|
1877 |
+
"nbytes": 10485760,
|
1878 |
+
"byteOffset": 18882560
|
1879 |
+
}
|
1880 |
+
],
|
1881 |
+
"md5sum": "551093d9636d08c36c4c4686750acd3d"
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"dataPath": "params_shard_57.bin",
|
1885 |
+
"format": "raw-shard",
|
1886 |
+
"nbytes": 8392704,
|
1887 |
+
"records": [
|
1888 |
+
{
|
1889 |
+
"name": "model.layers.9.self_attn.o_proj.weight",
|
1890 |
+
"shape": [
|
1891 |
+
2048,
|
1892 |
+
2048
|
1893 |
+
],
|
1894 |
+
"dtype": "float16",
|
1895 |
+
"format": "f32-to-bf16",
|
1896 |
+
"nbytes": 8388608,
|
1897 |
+
"byteOffset": 0
|
1898 |
+
},
|
1899 |
+
{
|
1900 |
+
"name": "model.norm.weight",
|
1901 |
+
"shape": [
|
1902 |
+
2048
|
1903 |
+
],
|
1904 |
+
"dtype": "float16",
|
1905 |
+
"format": "f32-to-bf16",
|
1906 |
+
"nbytes": 4096,
|
1907 |
+
"byteOffset": 8388608
|
1908 |
+
}
|
1909 |
+
],
|
1910 |
+
"md5sum": "67f5257abaa2b15cd8d1ad64db9b66fb"
|
1911 |
+
}
|
1912 |
+
]
|
1913 |
+
}
|
params_shard_0.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40bb78a2f956c07f89c7b222b3d4a5fef36b95bb75f430545016037832d749a4
|
3 |
+
size 131072000
|
params_shard_1.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a111cb9b6418f368b8905ab91eac077732d6ce2a54516acef6b9d060b921e23
|
3 |
+
size 131072000
|
params_shard_10.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:020f50c9099c72e6cbc9e29e1b433618e7be8d3ae676406f940e95aa08e3abd7
|
3 |
+
size 46137344
|
params_shard_11.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db9a3edf6a7d551b6b0b4509b0d81a0463e968d62b925bc110d89cd27be1a4b4
|
3 |
+
size 29368320
|
params_shard_12.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ccff959998f0cd563ad0c1d8b7f50638c35f3c637f2cfb9d852e823f94d6e26
|
3 |
+
size 46137344
|
params_shard_13.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ae491f096afafce65dc6074c3f2b5a0d08708cebcc8541290cee7cd6c3f78b51
|
3 |
+
size 31465472
|
params_shard_14.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2f0f263ad112a4442abf77c937fa804bfec28762cbde5978eff115bda4f3cbe
|
3 |
+
size 23068672
|
params_shard_15.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5ed89a02ad7e8c8236a1e2c736c8532b7e6dbcd265dd1f9105e5d778be6b408
|
3 |
+
size 46137344
|
params_shard_16.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c83ef8d58698af39b15a16abf7695cc97a03ae14ad55854ca1b286c0110a301b
|
3 |
+
size 29368320
|
params_shard_17.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e37d6540a65c7dacec2b4ce67633f6c7ed91836b22eb2b6ae76599ba00b25a9
|
3 |
+
size 46137344
|
params_shard_18.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed4fdbd2065a9a441f18fd49cad9e4574b0ff68d8470f1dc6f4883b012eb05d2
|
3 |
+
size 31465472
|
params_shard_19.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:675a9f9ec75a425220b60d6d5e61b2494baa59369adb552e2a10c253e6ef00f2
|
3 |
+
size 23068672
|
params_shard_2.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a0905ed98c87335db09a5be64892634dcccab88f80e96559446c2b5dd98d00d
|
3 |
+
size 46137344
|
params_shard_20.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2114c727fd7820c5bbba754e41a767c06c6356a25004350c1b1abcbd5a2b6fe1
|
3 |
+
size 46137344
|
params_shard_21.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41cf7031f92fa64eeaef78f1424f06bf1d3c41f79b30ac774d42f25fb1e948ee
|
3 |
+
size 29368320
|
params_shard_22.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a8428a8e6ca7de4a2d83a8bba4726a41d7ac1500b4da977fb369b8fc294ca4c
|
3 |
+
size 46137344
|
params_shard_23.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00aa64e12ec020678d462c711a045d8e506637d2c968d6a8b8080a614706fed7
|
3 |
+
size 31465472
|
params_shard_24.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53c4544e52c352a83e89a83cfe72dd22055569f934c1c9f42b185ca5ac9f55bd
|
3 |
+
size 23068672
|
params_shard_25.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff378f53234b4133e3cf27db35846206b46695d34476639c4338af6d95046b61
|
3 |
+
size 46137344
|
params_shard_26.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0303364f9058b7059f31d2414f180fdea5e64c830ca167deb4380ba4a9fde4be
|
3 |
+
size 29368320
|
params_shard_27.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:680913d9ee32d484dbfce6cc6c828e5ef9a4539f56a754dc0cf61a1251619364
|
3 |
+
size 46137344
|
params_shard_28.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2837196ceb01afb04f48f08eabaa73a9c91b263d5a56a1984f87d455f3a0e6d2
|
3 |
+
size 31465472
|
params_shard_29.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afe339e957b311b9d65ea475e98241d2fc876f46be639fb57a007abf892aa485
|
3 |
+
size 23068672
|
params_shard_3.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30e8cc52e3bced6491a2069b4caa0c323a681c478d025bba9f0e4e9c18307a28
|
3 |
+
size 23076864
|
params_shard_30.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8cde431a5a325c8c836bc725b1e03290b4b2b3392c1e05d9265d60ab5dc0827
|
3 |
+
size 46137344
|
params_shard_31.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:587659bd28cadbb1aa013075d9dc63fac39986da692338ffbd4cc34194877e14
|
3 |
+
size 29368320
|
params_shard_32.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5efc5884ac16737ee562635eb2fd5017ac9fa08f70b5570c6a3c90efab05645d
|
3 |
+
size 46137344
|
params_shard_33.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3050b22d0808793007ff2e131ad6a9feae1a77d0a078df9aa881d685ccd341aa
|
3 |
+
size 31465472
|
params_shard_34.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:880fd67b64c897b548c59a533446e17c87fdfb393e0491b7da659f282a8eb1af
|
3 |
+
size 23068672
|
params_shard_35.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ab077c6e52b3f1af4bbb9325d90a3f0016cebcbe4d5c0785691b43fd2cf5a59
|
3 |
+
size 46137344
|
params_shard_36.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d902a8da8c04e18386a4d9bee30c0377af9d8ae83292bd687f1830b5412621a
|
3 |
+
size 29368320
|
params_shard_37.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a72e03e5ab337070d2216a3465ff1faad6b78025ff29cde7fa23ee5574eb13bb
|
3 |
+
size 46137344
|
params_shard_38.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb9bdb2a535a1dd8a0389d3a321c5a00fe697311a389b0627e60acddd7366524
|
3 |
+
size 31465472
|
params_shard_39.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5361778fb63eaf705548c9d898e81833ab045b5c16387e230ad895f00a6c7770
|
3 |
+
size 23068672
|
params_shard_4.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7371bc0aee90c3e6b842680144853e81acaf338051574d3a81ebb0ccca657b2b
|
3 |
+
size 23068672
|
params_shard_40.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:316436340904a86ef38924eff36ac78889f44e5378e88cd7dba61a5b7c4d3565
|
3 |
+
size 46137344
|
params_shard_41.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab6d607609a711c6fc45e327e00e25457893b43b53750cdb97e1e3c9299c4c3f
|
3 |
+
size 29368320
|
params_shard_42.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f0262d846d32bf43003e22c55f567b9ecf057cc74f1f620aaf50e6837e36d3fd
|
3 |
+
size 46137344
|
params_shard_43.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77f5bca30386ca323a5ecba7204cd995ddf5454a7383cd1d1ca125b3499aaac2
|
3 |
+
size 31465472
|
params_shard_44.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94b51ac2c4c1cf091983061408391afe41e3c48501c9305bcfe806fbe68690d9
|
3 |
+
size 23068672
|
params_shard_45.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adde6e2c0ed2dce98c3f8f5500d7badeedf5e59860859d175ad7e5ea406390b3
|
3 |
+
size 46137344
|
params_shard_46.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09bb6bfe2fbe9404e752b6a1883bd5978f08c07d9155806646e5937f55f8cadf
|
3 |
+
size 29368320
|
params_shard_47.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db7fe0a95e0ee70122aa303b8f122ea8430647e8ec3fc57eab0cb0ae782fc494
|
3 |
+
size 46137344
|
params_shard_48.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6f94878e58f18236a18b3a034262abf934f1657be235aafd951fd37284df5a8
|
3 |
+
size 31465472
|
params_shard_49.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b20e65f65c33dc3884b6c1e7efc45009941851dd933b8b210adb6a4db04df07d
|
3 |
+
size 23068672
|
params_shard_5.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5dd1b6463c34d900410225ef11b4b0602ea9ae8fb65bd77b7a20b0dcbd0c279
|
3 |
+
size 46137344
|
params_shard_50.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:50127395351aa3645fb28ec6eda55b57a6572798638a7db42dd3f02d114a41ac
|
3 |
+
size 46137344
|