amychensima commited on
Commit
f0052a3
·
verified ·
1 Parent(s): c3e2475
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. console.log +55 -0
  2. devkit/precision.json +79 -79
  3. devkit/vlm_config.json +1 -0
  4. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token0_stage1_mla.elf +2 -2
  5. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1024_stage1_mla.elf +2 -2
  6. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1152_stage1_mla.elf +2 -2
  7. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1280_stage1_mla.elf +2 -2
  8. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token128_stage1_mla.elf +2 -2
  9. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1408_stage1_mla.elf +2 -2
  10. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1536_stage1_mla.elf +2 -2
  11. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1664_stage1_mla.elf +2 -2
  12. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1792_stage1_mla.elf +2 -2
  13. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1920_stage1_mla.elf +2 -2
  14. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token256_stage1_mla.elf +2 -2
  15. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token384_stage1_mla.elf +2 -2
  16. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token512_stage1_mla.elf +2 -2
  17. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token640_stage1_mla.elf +2 -2
  18. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token768_stage1_mla.elf +2 -2
  19. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token896_stage1_mla.elf +2 -2
  20. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer0_stage1_mla.elf +2 -2
  21. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer10_stage1_mla.elf +2 -2
  22. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer11_stage1_mla.elf +2 -2
  23. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer12_stage1_mla.elf +2 -2
  24. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer13_stage1_mla.elf +2 -2
  25. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer14_stage1_mla.elf +2 -2
  26. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer15_stage1_mla.elf +2 -2
  27. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer16_stage1_mla.elf +2 -2
  28. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer17_stage1_mla.elf +2 -2
  29. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer18_stage1_mla.elf +2 -2
  30. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer19_stage1_mla.elf +2 -2
  31. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer1_stage1_mla.elf +2 -2
  32. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer20_stage1_mla.elf +2 -2
  33. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer21_stage1_mla.elf +2 -2
  34. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer22_stage1_mla.elf +2 -2
  35. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer23_stage1_mla.elf +2 -2
  36. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer24_stage1_mla.elf +2 -2
  37. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer25_stage1_mla.elf +2 -2
  38. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer26_stage1_mla.elf +2 -2
  39. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer27_stage1_mla.elf +2 -2
  40. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer28_stage1_mla.elf +2 -2
  41. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer29_stage1_mla.elf +2 -2
  42. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer2_stage1_mla.elf +2 -2
  43. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer30_stage1_mla.elf +2 -2
  44. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer3_stage1_mla.elf +2 -2
  45. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer4_stage1_mla.elf +2 -2
  46. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer5_stage1_mla.elf +2 -2
  47. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer6_stage1_mla.elf +2 -2
  48. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer7_stage1_mla.elf +2 -2
  49. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer8_stage1_mla.elf +2 -2
  50. elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer9_stage1_mla.elf +2 -2
console.log ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
2
+ None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
3
+ VLM initialization starting ...
4
+ VLM initialization completed.
5
+ >>> Query: Why is the sky blue?
6
+ Assistant: The sky appears blue during the daytime due to a phenomenon called scattering. When sunlight enters Earth's atmosphere, it encounters tiny molecules of gases such as nitrogen and oxygen. These molecules scatter the light in all directions, but they scatter shorter (blue) wavelengths more than longer (red) wavelengths.
7
+
8
+ This is known as Rayleigh scattering, named after the British physicist Lord Rayleigh, who first described the phenomenon in the late 19th century. The scattered blue light is then reflected back to our eyes, making the sky appear blue.
9
+
10
+ The exact shade of blue can vary depending on several factors, such as:
11
+
12
+ 1. Atmospheric conditions: The amount of water vapor, dust, and pollutants in the atmosphere can affect the color of the sky.
13
+ 2. Time of day: The sky appears more vibrant during the daytime when the sun is overhead.
14
+ 3. Location: The color of the sky can differ depending on the location, with coastal areas often having a more intense blue hue due to the scattering of light by water droplets.
15
+ 4. Atmospheric conditions at sunrise and sunset: During these times, the sky can take on hues of red, orange, and pink due to the scattering of longer wavelengths.
16
+
17
+ In summary, the sky appears blue due to the scattering of sunlight by the tiny molecules in the atmosphere, with shorter wavelengths (blue light) being scattered more than longer wavelengths.
18
+
19
+ Number of generated tokens: 274
20
+ TTFT: 0.50s
21
+ TPS: avg=10.34, quantiles=['10.52', '10.34', '10.29', '10.24']
22
+ >>> Query: Summarize
23
+ Assistant: The sky appears blue during the daytime due to a phenomenon called scattering. When sunlight enters Earth's atmosphere, it encounters tiny molecules of gases that scatter shorter (blue) wavelengths more than longer (red) wavelengths, making the sky appear blue. The exact shade of blue can vary depending on atmospheric conditions, time of day, location, and atmospheric conditions at sunrise and sunset.
24
+
25
+ Number of generated tokens: 75
26
+ TTFT: 0.36s
27
+ TPS: avg=10.24, quantiles=['10.29', '10.28', '10.25', '10.14']
28
+ >>> Query: Tell me a story based on this
29
+ Assistant: Once upon a time, in a small village nestled between two great mountains, there lived a young girl named Luna. She was a curious and adventurous child, always fascinated by the vast expanse of the sky above her.
30
+
31
+ Every day, Luna would gaze up at the blue sky, mesmerized by its beauty. She wondered why the sky was blue, and her parents, though they didn't know the answer, encouraged her to keep exploring.
32
+
33
+ One day, Luna's curiosity led her to the wise old man who lived on the outskirts of the village. His name was Orion, and he was known for his vast knowledge of the world and its secrets.
34
+
35
+ Orion listened to Luna's question and smiled. "Come with me, little one," he said, and together they walked to a nearby hill overlooking the village.
36
+
37
+ As they reached the top, Orion pointed to the sky. "You see, Luna, the sky appears blue because of the way light behaves when it enters our atmosphere."
38
+
39
+ Luna's eyes widened with excitement as Orion explained the concept of scattering. "The tiny molecules of gases in the air scatter shorter wavelengths of light, like blue and violet, more than longer wavelengths, like red and orange," he said.
40
+
41
+ Orion then took Luna's hand and led her to a nearby pond. "Let's see how this works in action," he said, and together they watched as the sunlight danced across the water.
42
+
43
+ As the light passed through the water droplets, it scattered in all directions, casting a shimmering blue glow across the pond. Luna gasped in amazement, and Orion smiled. "You see, Luna, the same principle that makes the sky blue is at work here."
44
+
45
+ From that day on, Luna gazed up at the sky with a newfound understanding of its beauty. She knew that the blue hue was not just a simple color, but a result of the intricate dance of light and atmosphere.
46
+
47
+ As the sun began to set, casting a warm orange glow across the village, Luna turned to Orion with a question. "Why does the sky change color at sunset?" she asked.
48
+
49
+ Orion smiled, and together they watched as the sky transformed into a kaleidoscope of colors. "Ah, little one," he said, "that's a story for another time."
50
+
51
+ Number of generated tokens: 463
52
+ TTFT: 0.37s
53
+ TPS: avg=9.89, quantiles=['10.08', '10.03', '9.90', '9.58']
54
+ >>> WARN:starting syslog with prefix MLA-RT
55
+ ~MLALogger: logger is closed
devkit/precision.json CHANGED
@@ -2,397 +2,397 @@
2
  {
3
  "part": "group_pre",
4
  "idx": 0,
5
- "precision": "A_BF16_W_INT4"
6
  },
7
  {
8
  "part": "group_pre",
9
  "idx": 1,
10
- "precision": "A_BF16_W_INT4"
11
  },
12
  {
13
  "part": "group_pre",
14
  "idx": 2,
15
- "precision": "A_BF16_W_INT4"
16
  },
17
  {
18
  "part": "group_pre",
19
  "idx": 3,
20
- "precision": "A_BF16_W_INT4"
21
  },
22
  {
23
  "part": "group_pre",
24
  "idx": 4,
25
- "precision": "A_BF16_W_INT4"
26
  },
27
  {
28
  "part": "group_pre",
29
  "idx": 5,
30
- "precision": "A_BF16_W_INT4"
31
  },
32
  {
33
  "part": "group_pre",
34
  "idx": 6,
35
- "precision": "A_BF16_W_INT4"
36
  },
37
  {
38
  "part": "group_pre",
39
  "idx": 7,
40
- "precision": "A_BF16_W_INT4"
41
  },
42
  {
43
  "part": "group_pre",
44
  "idx": 8,
45
- "precision": "A_BF16_W_INT4"
46
  },
47
  {
48
  "part": "group_pre",
49
  "idx": 9,
50
- "precision": "A_BF16_W_INT4"
51
  },
52
  {
53
  "part": "group_pre",
54
  "idx": 10,
55
- "precision": "A_BF16_W_INT4"
56
  },
57
  {
58
  "part": "group_pre",
59
  "idx": 11,
60
- "precision": "A_BF16_W_INT4"
61
  },
62
  {
63
  "part": "group_pre",
64
  "idx": 12,
65
- "precision": "A_BF16_W_INT4"
66
  },
67
  {
68
  "part": "group_pre",
69
  "idx": 13,
70
- "precision": "A_BF16_W_INT4"
71
  },
72
  {
73
  "part": "group_pre",
74
  "idx": 14,
75
- "precision": "A_BF16_W_INT4"
76
  },
77
  {
78
  "part": "group_pre",
79
  "idx": 15,
80
- "precision": "A_BF16_W_INT4"
81
  },
82
  {
83
  "part": "group_pre",
84
  "idx": 16,
85
- "precision": "A_BF16_W_INT4"
86
  },
87
  {
88
  "part": "group_pre",
89
  "idx": 17,
90
- "precision": "A_BF16_W_INT4"
91
  },
92
  {
93
  "part": "group_pre",
94
  "idx": 18,
95
- "precision": "A_BF16_W_INT4"
96
  },
97
  {
98
  "part": "group_pre",
99
  "idx": 19,
100
- "precision": "A_BF16_W_INT4"
101
  },
102
  {
103
  "part": "group_pre",
104
  "idx": 20,
105
- "precision": "A_BF16_W_INT4"
106
  },
107
  {
108
  "part": "group_pre",
109
  "idx": 21,
110
- "precision": "A_BF16_W_INT4"
111
  },
112
  {
113
  "part": "group_pre",
114
  "idx": 22,
115
- "precision": "A_BF16_W_INT4"
116
  },
117
  {
118
  "part": "group_pre",
119
  "idx": 23,
120
- "precision": "A_BF16_W_INT4"
121
  },
122
  {
123
  "part": "group_pre",
124
  "idx": 24,
125
- "precision": "A_BF16_W_INT4"
126
  },
127
  {
128
  "part": "group_pre",
129
  "idx": 25,
130
- "precision": "A_BF16_W_INT4"
131
  },
132
  {
133
  "part": "group_pre",
134
  "idx": 26,
135
- "precision": "A_BF16_W_INT4"
136
  },
137
  {
138
  "part": "group_pre",
139
  "idx": 27,
140
- "precision": "A_BF16_W_INT4"
141
  },
142
  {
143
  "part": "group_pre",
144
  "idx": 28,
145
- "precision": "A_BF16_W_INT4"
146
  },
147
  {
148
  "part": "group_pre",
149
  "idx": 29,
150
- "precision": "A_BF16_W_INT4"
151
  },
152
  {
153
  "part": "group_pre",
154
  "idx": 30,
155
- "precision": "A_BF16_W_INT4"
156
  },
157
  {
158
  "part": "group_pre",
159
  "idx": 31,
160
- "precision": "A_BF16_W_INT4"
161
  },
162
  {
163
  "part": "group_post",
164
  "idx": 0,
165
- "precision": "A_BF16_W_INT4"
166
  },
167
  {
168
  "part": "group_post",
169
  "idx": 1,
170
- "precision": "A_BF16_W_INT4"
171
  },
172
  {
173
  "part": "group_post",
174
  "idx": 2,
175
- "precision": "A_BF16_W_INT4"
176
  },
177
  {
178
  "part": "group_post",
179
  "idx": 3,
180
- "precision": "A_BF16_W_INT4"
181
  },
182
  {
183
  "part": "group_post",
184
  "idx": 4,
185
- "precision": "A_BF16_W_INT4"
186
  },
187
  {
188
  "part": "group_post",
189
  "idx": 5,
190
- "precision": "A_BF16_W_INT4"
191
  },
192
  {
193
  "part": "group_post",
194
  "idx": 6,
195
- "precision": "A_BF16_W_INT4"
196
  },
197
  {
198
  "part": "group_post",
199
  "idx": 7,
200
- "precision": "A_BF16_W_INT4"
201
  },
202
  {
203
  "part": "group_post",
204
  "idx": 8,
205
- "precision": "A_BF16_W_INT4"
206
  },
207
  {
208
  "part": "group_post",
209
  "idx": 9,
210
- "precision": "A_BF16_W_INT4"
211
  },
212
  {
213
  "part": "group_post",
214
  "idx": 10,
215
- "precision": "A_BF16_W_INT4"
216
  },
217
  {
218
  "part": "group_post",
219
  "idx": 11,
220
- "precision": "A_BF16_W_INT4"
221
  },
222
  {
223
  "part": "group_post",
224
  "idx": 12,
225
- "precision": "A_BF16_W_INT4"
226
  },
227
  {
228
  "part": "group_post",
229
  "idx": 13,
230
- "precision": "A_BF16_W_INT4"
231
  },
232
  {
233
  "part": "group_post",
234
  "idx": 14,
235
- "precision": "A_BF16_W_INT4"
236
  },
237
  {
238
  "part": "group_post",
239
  "idx": 15,
240
- "precision": "A_BF16_W_INT4"
241
  },
242
  {
243
  "part": "group_post",
244
  "idx": 16,
245
- "precision": "A_BF16_W_INT4"
246
  },
247
  {
248
  "part": "group_post",
249
  "idx": 17,
250
- "precision": "A_BF16_W_INT4"
251
  },
252
  {
253
  "part": "group_post",
254
  "idx": 18,
255
- "precision": "A_BF16_W_INT4"
256
  },
257
  {
258
  "part": "group_post",
259
  "idx": 19,
260
- "precision": "A_BF16_W_INT4"
261
  },
262
  {
263
  "part": "group_post",
264
  "idx": 20,
265
- "precision": "A_BF16_W_INT4"
266
  },
267
  {
268
  "part": "group_post",
269
  "idx": 21,
270
- "precision": "A_BF16_W_INT4"
271
  },
272
  {
273
  "part": "group_post",
274
  "idx": 22,
275
- "precision": "A_BF16_W_INT4"
276
  },
277
  {
278
  "part": "group_post",
279
  "idx": 23,
280
- "precision": "A_BF16_W_INT4"
281
  },
282
  {
283
  "part": "group_post",
284
  "idx": 24,
285
- "precision": "A_BF16_W_INT4"
286
  },
287
  {
288
  "part": "group_post",
289
  "idx": 25,
290
- "precision": "A_BF16_W_INT4"
291
  },
292
  {
293
  "part": "group_post",
294
  "idx": 26,
295
- "precision": "A_BF16_W_INT4"
296
  },
297
  {
298
  "part": "group_post",
299
  "idx": 27,
300
- "precision": "A_BF16_W_INT4"
301
  },
302
  {
303
  "part": "group_post",
304
  "idx": 28,
305
- "precision": "A_BF16_W_INT4"
306
  },
307
  {
308
  "part": "group_post",
309
  "idx": 29,
310
- "precision": "A_BF16_W_INT4"
311
  },
312
  {
313
  "part": "group_post",
314
  "idx": 30,
315
- "precision": "A_BF16_W_INT4"
316
  },
317
  {
318
  "part": "group_cache",
319
  "idx": 0,
320
- "precision": "A_BF16_W_INT4"
321
  },
322
  {
323
  "part": "group_cache",
324
  "idx": 128,
325
- "precision": "A_BF16_W_INT4"
326
  },
327
  {
328
  "part": "group_cache",
329
  "idx": 256,
330
- "precision": "A_BF16_W_INT4"
331
  },
332
  {
333
  "part": "group_cache",
334
  "idx": 384,
335
- "precision": "A_BF16_W_INT4"
336
  },
337
  {
338
  "part": "group_cache",
339
  "idx": 512,
340
- "precision": "A_BF16_W_INT4"
341
  },
342
  {
343
  "part": "group_cache",
344
  "idx": 640,
345
- "precision": "A_BF16_W_INT4"
346
  },
347
  {
348
  "part": "group_cache",
349
  "idx": 768,
350
- "precision": "A_BF16_W_INT4"
351
  },
352
  {
353
  "part": "group_cache",
354
  "idx": 896,
355
- "precision": "A_BF16_W_INT4"
356
  },
357
  {
358
  "part": "group_cache",
359
  "idx": 1024,
360
- "precision": "A_BF16_W_INT4"
361
  },
362
  {
363
  "part": "group_cache",
364
  "idx": 1152,
365
- "precision": "A_BF16_W_INT4"
366
  },
367
  {
368
  "part": "group_cache",
369
  "idx": 1280,
370
- "precision": "A_BF16_W_INT4"
371
  },
372
  {
373
  "part": "group_cache",
374
  "idx": 1408,
375
- "precision": "A_BF16_W_INT4"
376
  },
377
  {
378
  "part": "group_cache",
379
  "idx": 1536,
380
- "precision": "A_BF16_W_INT4"
381
  },
382
  {
383
  "part": "group_cache",
384
  "idx": 1664,
385
- "precision": "A_BF16_W_INT4"
386
  },
387
  {
388
  "part": "group_cache",
389
  "idx": 1792,
390
- "precision": "A_BF16_W_INT4"
391
  },
392
  {
393
  "part": "group_cache",
394
  "idx": 1920,
395
- "precision": "A_BF16_W_INT4"
396
  },
397
  {
398
  "part": "single_pre",
 
2
  {
3
  "part": "group_pre",
4
  "idx": 0,
5
+ "precision": "A_BF16_W_INT8"
6
  },
7
  {
8
  "part": "group_pre",
9
  "idx": 1,
10
+ "precision": "A_BF16_W_INT8"
11
  },
12
  {
13
  "part": "group_pre",
14
  "idx": 2,
15
+ "precision": "A_BF16_W_INT8"
16
  },
17
  {
18
  "part": "group_pre",
19
  "idx": 3,
20
+ "precision": "A_BF16_W_INT8"
21
  },
22
  {
23
  "part": "group_pre",
24
  "idx": 4,
25
+ "precision": "A_BF16_W_INT8"
26
  },
27
  {
28
  "part": "group_pre",
29
  "idx": 5,
30
+ "precision": "A_BF16_W_INT8"
31
  },
32
  {
33
  "part": "group_pre",
34
  "idx": 6,
35
+ "precision": "A_BF16_W_INT8"
36
  },
37
  {
38
  "part": "group_pre",
39
  "idx": 7,
40
+ "precision": "A_BF16_W_INT8"
41
  },
42
  {
43
  "part": "group_pre",
44
  "idx": 8,
45
+ "precision": "A_BF16_W_INT8"
46
  },
47
  {
48
  "part": "group_pre",
49
  "idx": 9,
50
+ "precision": "A_BF16_W_INT8"
51
  },
52
  {
53
  "part": "group_pre",
54
  "idx": 10,
55
+ "precision": "A_BF16_W_INT8"
56
  },
57
  {
58
  "part": "group_pre",
59
  "idx": 11,
60
+ "precision": "A_BF16_W_INT8"
61
  },
62
  {
63
  "part": "group_pre",
64
  "idx": 12,
65
+ "precision": "A_BF16_W_INT8"
66
  },
67
  {
68
  "part": "group_pre",
69
  "idx": 13,
70
+ "precision": "A_BF16_W_INT8"
71
  },
72
  {
73
  "part": "group_pre",
74
  "idx": 14,
75
+ "precision": "A_BF16_W_INT8"
76
  },
77
  {
78
  "part": "group_pre",
79
  "idx": 15,
80
+ "precision": "A_BF16_W_INT8"
81
  },
82
  {
83
  "part": "group_pre",
84
  "idx": 16,
85
+ "precision": "A_BF16_W_INT8"
86
  },
87
  {
88
  "part": "group_pre",
89
  "idx": 17,
90
+ "precision": "A_BF16_W_INT8"
91
  },
92
  {
93
  "part": "group_pre",
94
  "idx": 18,
95
+ "precision": "A_BF16_W_INT8"
96
  },
97
  {
98
  "part": "group_pre",
99
  "idx": 19,
100
+ "precision": "A_BF16_W_INT8"
101
  },
102
  {
103
  "part": "group_pre",
104
  "idx": 20,
105
+ "precision": "A_BF16_W_INT8"
106
  },
107
  {
108
  "part": "group_pre",
109
  "idx": 21,
110
+ "precision": "A_BF16_W_INT8"
111
  },
112
  {
113
  "part": "group_pre",
114
  "idx": 22,
115
+ "precision": "A_BF16_W_INT8"
116
  },
117
  {
118
  "part": "group_pre",
119
  "idx": 23,
120
+ "precision": "A_BF16_W_INT8"
121
  },
122
  {
123
  "part": "group_pre",
124
  "idx": 24,
125
+ "precision": "A_BF16_W_INT8"
126
  },
127
  {
128
  "part": "group_pre",
129
  "idx": 25,
130
+ "precision": "A_BF16_W_INT8"
131
  },
132
  {
133
  "part": "group_pre",
134
  "idx": 26,
135
+ "precision": "A_BF16_W_INT8"
136
  },
137
  {
138
  "part": "group_pre",
139
  "idx": 27,
140
+ "precision": "A_BF16_W_INT8"
141
  },
142
  {
143
  "part": "group_pre",
144
  "idx": 28,
145
+ "precision": "A_BF16_W_INT8"
146
  },
147
  {
148
  "part": "group_pre",
149
  "idx": 29,
150
+ "precision": "A_BF16_W_INT8"
151
  },
152
  {
153
  "part": "group_pre",
154
  "idx": 30,
155
+ "precision": "A_BF16_W_INT8"
156
  },
157
  {
158
  "part": "group_pre",
159
  "idx": 31,
160
+ "precision": "A_BF16_W_INT8"
161
  },
162
  {
163
  "part": "group_post",
164
  "idx": 0,
165
+ "precision": "A_BF16_W_INT8"
166
  },
167
  {
168
  "part": "group_post",
169
  "idx": 1,
170
+ "precision": "A_BF16_W_INT8"
171
  },
172
  {
173
  "part": "group_post",
174
  "idx": 2,
175
+ "precision": "A_BF16_W_INT8"
176
  },
177
  {
178
  "part": "group_post",
179
  "idx": 3,
180
+ "precision": "A_BF16_W_INT8"
181
  },
182
  {
183
  "part": "group_post",
184
  "idx": 4,
185
+ "precision": "A_BF16_W_INT8"
186
  },
187
  {
188
  "part": "group_post",
189
  "idx": 5,
190
+ "precision": "A_BF16_W_INT8"
191
  },
192
  {
193
  "part": "group_post",
194
  "idx": 6,
195
+ "precision": "A_BF16_W_INT8"
196
  },
197
  {
198
  "part": "group_post",
199
  "idx": 7,
200
+ "precision": "A_BF16_W_INT8"
201
  },
202
  {
203
  "part": "group_post",
204
  "idx": 8,
205
+ "precision": "A_BF16_W_INT8"
206
  },
207
  {
208
  "part": "group_post",
209
  "idx": 9,
210
+ "precision": "A_BF16_W_INT8"
211
  },
212
  {
213
  "part": "group_post",
214
  "idx": 10,
215
+ "precision": "A_BF16_W_INT8"
216
  },
217
  {
218
  "part": "group_post",
219
  "idx": 11,
220
+ "precision": "A_BF16_W_INT8"
221
  },
222
  {
223
  "part": "group_post",
224
  "idx": 12,
225
+ "precision": "A_BF16_W_INT8"
226
  },
227
  {
228
  "part": "group_post",
229
  "idx": 13,
230
+ "precision": "A_BF16_W_INT8"
231
  },
232
  {
233
  "part": "group_post",
234
  "idx": 14,
235
+ "precision": "A_BF16_W_INT8"
236
  },
237
  {
238
  "part": "group_post",
239
  "idx": 15,
240
+ "precision": "A_BF16_W_INT8"
241
  },
242
  {
243
  "part": "group_post",
244
  "idx": 16,
245
+ "precision": "A_BF16_W_INT8"
246
  },
247
  {
248
  "part": "group_post",
249
  "idx": 17,
250
+ "precision": "A_BF16_W_INT8"
251
  },
252
  {
253
  "part": "group_post",
254
  "idx": 18,
255
+ "precision": "A_BF16_W_INT8"
256
  },
257
  {
258
  "part": "group_post",
259
  "idx": 19,
260
+ "precision": "A_BF16_W_INT8"
261
  },
262
  {
263
  "part": "group_post",
264
  "idx": 20,
265
+ "precision": "A_BF16_W_INT8"
266
  },
267
  {
268
  "part": "group_post",
269
  "idx": 21,
270
+ "precision": "A_BF16_W_INT8"
271
  },
272
  {
273
  "part": "group_post",
274
  "idx": 22,
275
+ "precision": "A_BF16_W_INT8"
276
  },
277
  {
278
  "part": "group_post",
279
  "idx": 23,
280
+ "precision": "A_BF16_W_INT8"
281
  },
282
  {
283
  "part": "group_post",
284
  "idx": 24,
285
+ "precision": "A_BF16_W_INT8"
286
  },
287
  {
288
  "part": "group_post",
289
  "idx": 25,
290
+ "precision": "A_BF16_W_INT8"
291
  },
292
  {
293
  "part": "group_post",
294
  "idx": 26,
295
+ "precision": "A_BF16_W_INT8"
296
  },
297
  {
298
  "part": "group_post",
299
  "idx": 27,
300
+ "precision": "A_BF16_W_INT8"
301
  },
302
  {
303
  "part": "group_post",
304
  "idx": 28,
305
+ "precision": "A_BF16_W_INT8"
306
  },
307
  {
308
  "part": "group_post",
309
  "idx": 29,
310
+ "precision": "A_BF16_W_INT8"
311
  },
312
  {
313
  "part": "group_post",
314
  "idx": 30,
315
+ "precision": "A_BF16_W_INT8"
316
  },
317
  {
318
  "part": "group_cache",
319
  "idx": 0,
320
+ "precision": "A_BF16_W_INT8"
321
  },
322
  {
323
  "part": "group_cache",
324
  "idx": 128,
325
+ "precision": "A_BF16_W_INT8"
326
  },
327
  {
328
  "part": "group_cache",
329
  "idx": 256,
330
+ "precision": "A_BF16_W_INT8"
331
  },
332
  {
333
  "part": "group_cache",
334
  "idx": 384,
335
+ "precision": "A_BF16_W_INT8"
336
  },
337
  {
338
  "part": "group_cache",
339
  "idx": 512,
340
+ "precision": "A_BF16_W_INT8"
341
  },
342
  {
343
  "part": "group_cache",
344
  "idx": 640,
345
+ "precision": "A_BF16_W_INT8"
346
  },
347
  {
348
  "part": "group_cache",
349
  "idx": 768,
350
+ "precision": "A_BF16_W_INT8"
351
  },
352
  {
353
  "part": "group_cache",
354
  "idx": 896,
355
+ "precision": "A_BF16_W_INT8"
356
  },
357
  {
358
  "part": "group_cache",
359
  "idx": 1024,
360
+ "precision": "A_BF16_W_INT8"
361
  },
362
  {
363
  "part": "group_cache",
364
  "idx": 1152,
365
+ "precision": "A_BF16_W_INT8"
366
  },
367
  {
368
  "part": "group_cache",
369
  "idx": 1280,
370
+ "precision": "A_BF16_W_INT8"
371
  },
372
  {
373
  "part": "group_cache",
374
  "idx": 1408,
375
+ "precision": "A_BF16_W_INT8"
376
  },
377
  {
378
  "part": "group_cache",
379
  "idx": 1536,
380
+ "precision": "A_BF16_W_INT8"
381
  },
382
  {
383
  "part": "group_cache",
384
  "idx": 1664,
385
+ "precision": "A_BF16_W_INT8"
386
  },
387
  {
388
  "part": "group_cache",
389
  "idx": 1792,
390
+ "precision": "A_BF16_W_INT8"
391
  },
392
  {
393
  "part": "group_cache",
394
  "idx": 1920,
395
+ "precision": "A_BF16_W_INT8"
396
  },
397
  {
398
  "part": "single_pre",
devkit/vlm_config.json CHANGED
@@ -58,6 +58,7 @@
58
  },
59
  "pipeline_cfg": {
60
  "system_prompt": null,
 
61
  "max_num_tokens": 2048,
62
  "input_token_group_size": 128,
63
  "input_token_group_offsets": [
 
58
  },
59
  "pipeline_cfg": {
60
  "system_prompt": null,
61
+ "chat_template": null,
62
  "max_num_tokens": 2048,
63
  "input_token_group_size": 128,
64
  "input_token_group_offsets": [
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token0_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0da428be41df538792c8e9b9b83c38356cd5a2c973708ab1be766206d7206098
3
- size 4255048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba724aea0dc6a0d8c230c76efbcfaa41a0473b7879affb983b07b8520d382ade
3
+ size 4240008
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1024_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90ee1572fb965f1dcc0ed49c7d3c16572cc4070535d3cb5fa2052aca33ad8c4c
3
- size 13483800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1569218f4aa8b1b54829891e794ed6efb8c6c16f8f14e9cfd90180a600a049c0
3
+ size 11947200
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1152_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9a640f700e44ce410c56756ddaee15ceb82fb61680c273b6321155ab959dc74
3
- size 29341048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a7ba2c87d3e6ab8191f521f00861e0c7d7fde6bb583178d6ae390615f2ec34
3
+ size 14312472
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1280_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff22d8330728f66b6edfdb173ab037b8dc851b359476736840de3b4353ad3930
3
- size 21418496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc6dda722a81b358485bcbd0606de93621f8fad22c3c839dc8ea4dc3ba5d0b08
3
+ size 13877000
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token128_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6df068020c5fe11de3dba1ec9fc1f8db1e38043191ff46620cf0fa7257df4446
3
- size 3987872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:639cb8f4f49b2f624a815474161645391afad2b2b37271aa7cbcb8895e2625fb
3
+ size 4589520
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1408_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:09b0606a97cacda3e4243fbd552d56245e77b950ef56da75bfecc8dbec9d8489
3
- size 16404624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad5fb7a926bab94f2e98c3fe2578ec0993be31383be43c6d0fbab61604d80f01
3
+ size 16241328
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1536_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4fd7844d72cbb8c7877598b99784c46c88d3069bc16b72c4f88d5b5573320b4
3
- size 18398736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abdf6292fb16e77195c88df8851425c3a8173108b60f44c7852b7dd56f34fc7b
3
+ size 17234088
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1664_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c94847d1e1ca8138d679b78bea181fc44e693cce2aaee476e0854f00de301199
3
- size 25833952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccc8ff28a433eae845d07efae7b125075bdf5a6ffaaff67092b315c3591c8c33
3
+ size 17028872
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1792_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:729ce713cba06403b16ae9b8649a7b5d88b051103f23cb546f51071a797ecfe8
3
- size 24244896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2868e8f48e23a3e89b2a98989d46379e5231c924d4bb4d4664ee9d799865b2f9
3
+ size 17311688
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token1920_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5f95bd57f48fdda4fff97fe45e4165982b5c1c5e443d5d8dcd189f44dd1b3fc
3
- size 22310712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22b42a28516b44612d0ab19ef6a56506f2f9d46807e571225dd99d7790b70db1
3
+ size 18200312
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token256_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bc3b9ecce22eda02ac3fdaf2ead6ed0056c9e7e8969e3576580eaf4fc89dca7
3
- size 4993840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31b7dfe79de0351c7c30a4e63bd79771906503b748e1fa394e4d058a062278f2
3
+ size 4716480
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token384_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:430db8c450938c88639e0c6947e24396bd24b2d2662904f67abf06eb6260b245
3
- size 4963368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6fd90a4b014524f2c87959d24af47113274fb6ed17bda3278a67520382ba3f1
3
+ size 6127904
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token512_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58450c2d9e06413ac4465512d85b15b51e149080dfb856deb6be9715abec5914
3
- size 10014392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee6486094acbe67bb973d35f42cdfd1924e63afb964edc0162f1190c07211e93
3
+ size 6492640
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token640_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e02c0658847bdbffb119ffa9edcf525a9968ebb3ca4b65aea41415506a6f6ddb
3
- size 7789352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec78715db445f7ec8e7e606d3ef3bf4849737761a4ef67d767b81f98defc752
3
+ size 7985248
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token768_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22cfb5a63b3a4f29d700c1aef8bf59a2ee4b3ee825ca50d1721e2e2c2b6a20c6
3
- size 11864064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0ad480cf617b7f4682bebc93f927e76d41d90963349aa17970c020a72bfae81
3
+ size 10248464
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_cache_token896_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0d084494582fe56742a179cdd6bb1fa826ae1dac3cc1999377f7de9fc797046
3
- size 11120552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3fce3702e46becc453470468a054a093fa093cc3e771105912ed02182d7dd5a
3
+ size 10592440
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer0_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7da72b2ab5adea0d304dda998f146c29b3075ae707928193b374013e486faade
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e315842eccdc74b7fbb5f1ce8bc06b1c0c5401e44f97fbe2c8dfb56b1bb285ce
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer10_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b68f00e396df13cffe42e537caa39836899fb3f8bf9f98dcee3b3070e0429ebb
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad2ebf7f0a87eef028f86be600540d59e0a4952692a556bccaf56ca91a910fa9
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer11_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11f8bae450aa3737a4c558939106083f680d45e9e28856a0b2920dc2b858507e
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af2a4cb461fd6511ab1c1f5a691cf35a0ca36c373879cb45209b3bc1cc799aba
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer12_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02c14644189a39609748d33d3b041088a207340cdb217345f6f9d1ca47a66a52
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1edcbd564333859df0e8b51d3dc8a9d53c392b8b9852aa89ee36deb8507729f6
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer13_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47d1a4bf8117ed6ac9801c889bcd4b86bfa3a9156f16698199ef66b048f6c5ac
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5cc6157e9f5000f9d11911bd4ba5ceab68cfc5140b4475e03ab2aab8dd854dd
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer14_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df3bf4f5fdd9b4eb248aa8e2dfcc009e1ea1f5ee1cc6b9c42fad5a220e343eb3
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dea279f174399196635d3fac10591c880c6267b1c730a58d7e6f2a8fddff858
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer15_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa8eb06307af9190edd32d81e682128c33c1c2437c1efad267d5873668f43bd1
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bbc0359c7743c37ab43f0bf63cca9149a07d2655222c76acaa6c75751b7de18
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer16_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77cc8781cc0bc3dd605cee8b3f377d7705058acd6c0561954d77617a7d8bb7d6
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d9d735385bf2652360201b5b40bd2af6e6a714c7ef3216f6bdc58f347c7cfe
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer17_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:345336bebe0a9d3a1dd56c9194ec49fe5fcbc1196e44e690e621c09b90d27182
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e524df6b35f3234b67b496d9591b40d3e1348c9243f343f836cf6a432ad061e4
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer18_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bffb38a346c81f055227e20dab1de2d480915f1a6b510062bbd128d3360327a
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0699348ee6adf3aac0ea671e3eac87174b38f74df8aaefc3d5a47dfacfefc28
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer19_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cdb744976ee6ac4a1a8560f9fb5713b6cbcb2901aeb937599a510f5e1bda896
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:178334ff3bced4ca56d2ca805c1dbed2f43555d2aa766d1c0a1ece87cb10650f
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer1_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0703e8cc201209ff70167806fc4162e19cb6c5b7760347fe0287c3241a9e1543
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02ee935528cd9710e2f07c7d54cd8cfa883cf06beaeccab034213ce2e58d1485
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer20_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1ccb64fcb7f4284239c7e2730a8aea9db63dd2f20e1da529f4b4f59e53f12ef
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27c848bdb3aaa684bfb29ab699114ffbf75951fd3f6e9b9ab95db89a6bf6e0bd
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer21_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e8c9e510063a382af4cba5f01990e30a4a4b557caea4c993d1ad3013481ff6a
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf0b23fb7e46e578a5c4c5a9d50cb35c84b25b1eff5d2b03a926db329c741014
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer22_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d3aee798cf2d25edac6e185f5192722969934ee0051e6b7e1b4ea0bd65f19ae
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25d7e651e0889e96d222d4628bf508c6bc910381245acea656a0151f099e779b
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer23_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07a446e40eda68080c60d13cdd5299a06ed0566ad968b09e9e5ba8a8f209758f
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e170461d64f7db87359749749000c1034613f15500b13cc6efcf530a60d2d89
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer24_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c786e343be63da259acba7c459ac04d77513d6bb43968912a2310ce78f9110c2
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20e6ea89b33b9faa4b437218da41b7a74af481d1e53e3ca7593fbc0c75ee460c
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer25_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cd1d5602bb7311e2becd77027f3abb8996b9449d8997d5a3648ff3de383a585
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c705a982d89337463bfcbff4ee1e3607bbca6da1cf3027c628a1e570af68355
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer26_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f166fbc90886169d7c3ebb06e47bbcda60661cf41afe33cdd4bf96e6f899b6f9
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3a6c6b82732a869b7a0ce20982c83a29b2fb2aa9251f8d8c913528feed5d123
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer27_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e9a24d2bf7bbfefa87b7c787b7e8346ac4881829f0cb2aab5d55afe4945e918
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:871a1de5a49562ab370dbe7225f88959c847e4b8909a38d86fd197bb4f1bb06b
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer28_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecc934d0e440858032bfbee670cbee69bf1169082eb636051fb9ee0e88a935ff
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02221bbd4682787b4c2fd7bfc600f185dcde039c8c9e5019b75d2bdfe88c685b
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer29_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f64ff8442d38d2de7c3af1b85f1c6bc1f1b615abfc1a7d6702248eddb26d9e1
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f44d6ee168e20084eebbc2a5730110f4003c52b5698e1dfd82a0e8ba6c34350
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer2_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85259ab2c4c75d5a2c795a799c4749e568e9323f58ccb66d2ce6fc7e837c8ddf
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3437ae17ea3055a4fbdaccb639a7bad4f852f0738c552cdcaa16a614a04a172
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer30_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b80dd20369707f3e8a32a646be445166d31f9e71921ec9a6847b52a7f15e430
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1858757f333a90abeb418c096ee120d18c1a82e622fac22cd8acc240c1fb3d6
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer3_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02e1860b1f97b5d080a7852765f40e6643961b23552f1c14cbb548a1efc9a767
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccca12ddc72541aceb809f980a97e4b3e8ed0f375eceaa6cea526f54acac23c0
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer4_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56b35cf456774ca4af39f8e03c8be0b7afe1ce61cfaf06aaa8059c85b7b4bc0e
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce5fcb7e7a1465157ee0963cbb56720ef2b996f743540936110b981a631f5dae
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer5_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61846480e3b61a941ddf502bb14fa8064fee4f104367f164b4af917f39ee1e78
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:772a6a0bcebe5c3e483beb71a7186f89251c9fde5d12701e2ed83650c6beb011
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer6_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0585c02cb2a6f55ed1922ebbdf0368971f1a8c21d457d0d1e09b9107bc1b617
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:886ec37d5445ca9b31791d804e9d4daa9bf101ea1802e303efc51e47866c230e
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer7_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca7881c31b977139f8d11eb509deb715150b3191f5882fd7db3734070649d1ad
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c247cc93ec81f0c3413f2c45e1a9efc0618cb0c160c33bb60c6456f334fbde31
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer8_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0db8e2aea4a2dfba06db80b8a4a4efa53120e7c9baa7133ce57d5305aa37537c
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:643a29cdfb5ac8c51627ebf5ed99516227f78dec1064229a33c2abf43c661349
3
+ size 220746936
elf_files/models--meta-llama--Llama-3.1-8B-Instruct_language_n128_post_layer9_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd8f941b38e2cad629ed331f00a61a825f0693561465e931cc0604757a9efd4b
3
- size 367118008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c542a19f7ad2039141f777ecbb19d4f84127cf53468a82bd71ae4e636c5b9212
3
+ size 220746936