Hugging Face's logo

simaai
/
Llama-3.2-3B-Instruct-a16w4

Text Generation
GGUF
llima
llm
generative_ai
embedded
sima
conversational
Model card Files
xet
Community
2
amychensima commited on
Commit
b06bd6f
·
verified ·
1 Parent(s): 7bb2f7a

2.0.0

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. console.log +53 -0
  2. devkit/precision.json +71 -71
  3. devkit/vlm_config.json +1 -0
  4. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token0_stage1_mla.elf +2 -2
  5. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token1024_stage1_mla.elf +2 -2
  6. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token1152_stage1_mla.elf +2 -2
  7. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token1280_stage1_mla.elf +2 -2
  8. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token128_stage1_mla.elf +2 -2
  9. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token1408_stage1_mla.elf +2 -2
  10. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token1536_stage1_mla.elf +2 -2
  11. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token1664_stage1_mla.elf +2 -2
  12. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token1792_stage1_mla.elf +2 -2
  13. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token1920_stage1_mla.elf +2 -2
  14. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token256_stage1_mla.elf +2 -2
  15. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token384_stage1_mla.elf +2 -2
  16. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token512_stage1_mla.elf +2 -2
  17. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token640_stage1_mla.elf +2 -2
  18. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token768_stage1_mla.elf +2 -2
  19. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token896_stage1_mla.elf +2 -2
  20. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer0_stage1_mla.elf +2 -2
  21. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer10_stage1_mla.elf +2 -2
  22. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer11_stage1_mla.elf +2 -2
  23. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer12_stage1_mla.elf +2 -2
  24. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer13_stage1_mla.elf +2 -2
  25. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer14_stage1_mla.elf +2 -2
  26. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer15_stage1_mla.elf +2 -2
  27. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer16_stage1_mla.elf +2 -2
  28. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer17_stage1_mla.elf +2 -2
  29. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer18_stage1_mla.elf +2 -2
  30. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer19_stage1_mla.elf +2 -2
  31. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer1_stage1_mla.elf +2 -2
  32. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer20_stage1_mla.elf +2 -2
  33. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer21_stage1_mla.elf +2 -2
  34. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer22_stage1_mla.elf +2 -2
  35. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer23_stage1_mla.elf +2 -2
  36. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer24_stage1_mla.elf +2 -2
  37. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer25_stage1_mla.elf +2 -2
  38. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer26_stage1_mla.elf +2 -2
  39. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer2_stage1_mla.elf +2 -2
  40. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer3_stage1_mla.elf +2 -2
  41. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer4_stage1_mla.elf +2 -2
  42. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer5_stage1_mla.elf +2 -2
  43. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer6_stage1_mla.elf +2 -2
  44. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer7_stage1_mla.elf +2 -2
  45. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer8_stage1_mla.elf +2 -2
  46. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer9_stage1_mla.elf +2 -2
  47. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_pre_layer0_stage1_mla.elf +2 -2
  48. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_pre_layer10_stage1_mla.elf +2 -2
  49. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_pre_layer11_stage1_mla.elf +2 -2
  50. elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_pre_layer12_stage1_mla.elf +2 -2
console.log ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 because of a phenomenon called Rayleigh scattering, named after the British physicist Lord Rayleigh, who first explained it in the late 19th century.
7
+
8
+ Here's what happens:
9
+
10
+ 1. **Sunlight enters Earth's atmosphere**: When sunlight enters our atmosphere, it encounters tiny molecules of gases like nitrogen (N2) and oxygen (O2).
11
+ 2. **Scattering occurs**: These gas molecules scatter the light in all directions, but they scatter shorter (blue) wavelengths more than longer (red) wavelengths. This is known as Rayleigh scattering.
12
+ 3. **Blue light is scattered**: As a result, the blue light is scattered in all directions, making the sky appear blue to our eyes.
13
+ 4. **Red light continues to travel**: The longer wavelengths of light, like red and orange, continue to travel in a straight line, reaching our eyes from a more direct path.
14
+
15
+ This is why the sky typically appears blue during the daytime, especially during clear weather. At sunrise and sunset, the light has to travel through more of the atmosphere, which scatters the shorter wavelengths even more, making the sky appear more red or orange.
16
+
17
+ It's worth noting that the color of the sky can vary depending on atmospheric conditions, like pollution, dust, and water vapor. For example, during a severe thunderstorm or in areas with high levels of pollution, the sky can appear more gray or hazy.
18
+
19
+ So, to summarize, the sky appears blue due to the scattering of sunlight by tiny molecules in the atmosphere, which scatters shorter wavelengths (like blue light) more than longer wavelengths (like red light).
20
+
21
+ Number of generated tokens: 327
22
+ TTFT: 0.21s
23
+ TPS: avg=19.64, quantiles=['20.03', '19.63', '19.58', '19.35']
24
+ >>> Query: Summarize
25
+ Assistant: The sky appears blue due to Rayleigh scattering, where tiny molecules in the atmosphere scatter sunlight, scattering shorter (blue) wavelengths more than longer (red) wavelengths. This scattering occurs when sunlight enters the Earth's atmosphere and encounters gas molecules like nitrogen and oxygen. As a result, blue light is scattered in all directions, making the sky appear blue to our eyes.
26
+
27
+ Number of generated tokens: 74
28
+ TTFT: 0.13s
29
+ TPS: avg=19.10, quantiles=['19.12', '19.10', '19.08', '19.07']
30
+ >>> Query: Tell me a story based on this
31
+ Assistant: Once upon a time, in a small village nestled between two great mountains, there lived a young girl named Luna. Luna was fascinated by the sky and spent most of her days gazing up at it, trying to understand its secrets.
32
+
33
+ One day, while exploring the village, Luna stumbled upon an old wise man named Atlas. Atlas was a master of the stars and the secrets of the universe. He had spent his life studying the movements of the planets and the behavior of light.
34
+
35
+ Luna approached Atlas with a curious mind and a burning question: "Why is the sky blue?" Atlas smiled and began to tell her a story.
36
+
37
+ "Long ago," Atlas said, "the sky was not blue. It was a deep, fiery red, like the embers of a dying fire. But one day, a great storm swept through the land, bringing with it tiny particles of dust and gas. These particles danced in the air, scattering the light of the sun in all directions."
38
+
39
+ Luna's eyes widened with wonder as Atlas continued. "The blue light, being the shortest and most energetic of all, was scattered the most. It bounced off the particles and filled the air with a brilliant blue hue. And so, the sky became blue, a reflection of the beauty and wonder of the universe."
40
+
41
+ Luna listened, entranced, as Atlas told her of the ancient Greeks who had first discovered the secret of the blue sky. She learned of the great scientists who had studied the behavior of light and the tiny molecules that scattered it.
42
+
43
+ As the sun began to set, casting a warm orange glow over the village, Luna looked up at the sky and saw the blue hue for the first time. She felt a sense of wonder and awe, knowing that the sky was not just a simple reflection of the sun's light, but a complex and beautiful dance of particles and light.
44
+
45
+ From that day on, Luna spent every clear night gazing up at the sky, searching for the secrets of the universe and the magic of the blue light that made it all possible. And Atlas, the wise old man, watched over her, guiding her on her journey of discovery and wonder.
46
+
47
+ The story of the blue sky became a legend, passed down through generations of villagers, a reminder of the beauty and wonder of the universe and the magic that lay just beyond the edge of our everyday world.
48
+
49
+ Number of generated tokens: 476
50
+ TTFT: 0.13s
51
+ TPS: avg=18.45, quantiles=['18.80', '18.50', '18.30', '18.09']
52
+ >>> WARN:starting syslog with prefix MLA-RT
53
+ ~MLALogger: logger is closed
devkit/precision.json CHANGED
@@ -2,357 +2,357 @@
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_post",
144
  "idx": 0,
145
- "precision": "A_BF16_W_INT4"
146
  },
147
  {
148
  "part": "group_post",
149
  "idx": 1,
150
- "precision": "A_BF16_W_INT4"
151
  },
152
  {
153
  "part": "group_post",
154
  "idx": 2,
155
- "precision": "A_BF16_W_INT4"
156
  },
157
  {
158
  "part": "group_post",
159
  "idx": 3,
160
- "precision": "A_BF16_W_INT4"
161
  },
162
  {
163
  "part": "group_post",
164
  "idx": 4,
165
- "precision": "A_BF16_W_INT4"
166
  },
167
  {
168
  "part": "group_post",
169
  "idx": 5,
170
- "precision": "A_BF16_W_INT4"
171
  },
172
  {
173
  "part": "group_post",
174
  "idx": 6,
175
- "precision": "A_BF16_W_INT4"
176
  },
177
  {
178
  "part": "group_post",
179
  "idx": 7,
180
- "precision": "A_BF16_W_INT4"
181
  },
182
  {
183
  "part": "group_post",
184
  "idx": 8,
185
- "precision": "A_BF16_W_INT4"
186
  },
187
  {
188
  "part": "group_post",
189
  "idx": 9,
190
- "precision": "A_BF16_W_INT4"
191
  },
192
  {
193
  "part": "group_post",
194
  "idx": 10,
195
- "precision": "A_BF16_W_INT4"
196
  },
197
  {
198
  "part": "group_post",
199
  "idx": 11,
200
- "precision": "A_BF16_W_INT4"
201
  },
202
  {
203
  "part": "group_post",
204
  "idx": 12,
205
- "precision": "A_BF16_W_INT4"
206
  },
207
  {
208
  "part": "group_post",
209
  "idx": 13,
210
- "precision": "A_BF16_W_INT4"
211
  },
212
  {
213
  "part": "group_post",
214
  "idx": 14,
215
- "precision": "A_BF16_W_INT4"
216
  },
217
  {
218
  "part": "group_post",
219
  "idx": 15,
220
- "precision": "A_BF16_W_INT4"
221
  },
222
  {
223
  "part": "group_post",
224
  "idx": 16,
225
- "precision": "A_BF16_W_INT4"
226
  },
227
  {
228
  "part": "group_post",
229
  "idx": 17,
230
- "precision": "A_BF16_W_INT4"
231
  },
232
  {
233
  "part": "group_post",
234
  "idx": 18,
235
- "precision": "A_BF16_W_INT4"
236
  },
237
  {
238
  "part": "group_post",
239
  "idx": 19,
240
- "precision": "A_BF16_W_INT4"
241
  },
242
  {
243
  "part": "group_post",
244
  "idx": 20,
245
- "precision": "A_BF16_W_INT4"
246
  },
247
  {
248
  "part": "group_post",
249
  "idx": 21,
250
- "precision": "A_BF16_W_INT4"
251
  },
252
  {
253
  "part": "group_post",
254
  "idx": 22,
255
- "precision": "A_BF16_W_INT4"
256
  },
257
  {
258
  "part": "group_post",
259
  "idx": 23,
260
- "precision": "A_BF16_W_INT4"
261
  },
262
  {
263
  "part": "group_post",
264
  "idx": 24,
265
- "precision": "A_BF16_W_INT4"
266
  },
267
  {
268
  "part": "group_post",
269
  "idx": 25,
270
- "precision": "A_BF16_W_INT4"
271
  },
272
  {
273
  "part": "group_post",
274
  "idx": 26,
275
- "precision": "A_BF16_W_INT4"
276
  },
277
  {
278
  "part": "group_cache",
279
  "idx": 0,
280
- "precision": "A_BF16_W_INT4"
281
  },
282
  {
283
  "part": "group_cache",
284
  "idx": 128,
285
- "precision": "A_BF16_W_INT4"
286
  },
287
  {
288
  "part": "group_cache",
289
  "idx": 256,
290
- "precision": "A_BF16_W_INT4"
291
  },
292
  {
293
  "part": "group_cache",
294
  "idx": 384,
295
- "precision": "A_BF16_W_INT4"
296
  },
297
  {
298
  "part": "group_cache",
299
  "idx": 512,
300
- "precision": "A_BF16_W_INT4"
301
  },
302
  {
303
  "part": "group_cache",
304
  "idx": 640,
305
- "precision": "A_BF16_W_INT4"
306
  },
307
  {
308
  "part": "group_cache",
309
  "idx": 768,
310
- "precision": "A_BF16_W_INT4"
311
  },
312
  {
313
  "part": "group_cache",
314
  "idx": 896,
315
- "precision": "A_BF16_W_INT4"
316
  },
317
  {
318
  "part": "group_cache",
319
  "idx": 1024,
320
- "precision": "A_BF16_W_INT4"
321
  },
322
  {
323
  "part": "group_cache",
324
  "idx": 1152,
325
- "precision": "A_BF16_W_INT4"
326
  },
327
  {
328
  "part": "group_cache",
329
  "idx": 1280,
330
- "precision": "A_BF16_W_INT4"
331
  },
332
  {
333
  "part": "group_cache",
334
  "idx": 1408,
335
- "precision": "A_BF16_W_INT4"
336
  },
337
  {
338
  "part": "group_cache",
339
  "idx": 1536,
340
- "precision": "A_BF16_W_INT4"
341
  },
342
  {
343
  "part": "group_cache",
344
  "idx": 1664,
345
- "precision": "A_BF16_W_INT4"
346
  },
347
  {
348
  "part": "group_cache",
349
  "idx": 1792,
350
- "precision": "A_BF16_W_INT4"
351
  },
352
  {
353
  "part": "group_cache",
354
  "idx": 1920,
355
- "precision": "A_BF16_W_INT4"
356
  },
357
  {
358
  "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_post",
144
  "idx": 0,
145
+ "precision": "A_BF16_W_INT8"
146
  },
147
  {
148
  "part": "group_post",
149
  "idx": 1,
150
+ "precision": "A_BF16_W_INT8"
151
  },
152
  {
153
  "part": "group_post",
154
  "idx": 2,
155
+ "precision": "A_BF16_W_INT8"
156
  },
157
  {
158
  "part": "group_post",
159
  "idx": 3,
160
+ "precision": "A_BF16_W_INT8"
161
  },
162
  {
163
  "part": "group_post",
164
  "idx": 4,
165
+ "precision": "A_BF16_W_INT8"
166
  },
167
  {
168
  "part": "group_post",
169
  "idx": 5,
170
+ "precision": "A_BF16_W_INT8"
171
  },
172
  {
173
  "part": "group_post",
174
  "idx": 6,
175
+ "precision": "A_BF16_W_INT8"
176
  },
177
  {
178
  "part": "group_post",
179
  "idx": 7,
180
+ "precision": "A_BF16_W_INT8"
181
  },
182
  {
183
  "part": "group_post",
184
  "idx": 8,
185
+ "precision": "A_BF16_W_INT8"
186
  },
187
  {
188
  "part": "group_post",
189
  "idx": 9,
190
+ "precision": "A_BF16_W_INT8"
191
  },
192
  {
193
  "part": "group_post",
194
  "idx": 10,
195
+ "precision": "A_BF16_W_INT8"
196
  },
197
  {
198
  "part": "group_post",
199
  "idx": 11,
200
+ "precision": "A_BF16_W_INT8"
201
  },
202
  {
203
  "part": "group_post",
204
  "idx": 12,
205
+ "precision": "A_BF16_W_INT8"
206
  },
207
  {
208
  "part": "group_post",
209
  "idx": 13,
210
+ "precision": "A_BF16_W_INT8"
211
  },
212
  {
213
  "part": "group_post",
214
  "idx": 14,
215
+ "precision": "A_BF16_W_INT8"
216
  },
217
  {
218
  "part": "group_post",
219
  "idx": 15,
220
+ "precision": "A_BF16_W_INT8"
221
  },
222
  {
223
  "part": "group_post",
224
  "idx": 16,
225
+ "precision": "A_BF16_W_INT8"
226
  },
227
  {
228
  "part": "group_post",
229
  "idx": 17,
230
+ "precision": "A_BF16_W_INT8"
231
  },
232
  {
233
  "part": "group_post",
234
  "idx": 18,
235
+ "precision": "A_BF16_W_INT8"
236
  },
237
  {
238
  "part": "group_post",
239
  "idx": 19,
240
+ "precision": "A_BF16_W_INT8"
241
  },
242
  {
243
  "part": "group_post",
244
  "idx": 20,
245
+ "precision": "A_BF16_W_INT8"
246
  },
247
  {
248
  "part": "group_post",
249
  "idx": 21,
250
+ "precision": "A_BF16_W_INT8"
251
  },
252
  {
253
  "part": "group_post",
254
  "idx": 22,
255
+ "precision": "A_BF16_W_INT8"
256
  },
257
  {
258
  "part": "group_post",
259
  "idx": 23,
260
+ "precision": "A_BF16_W_INT8"
261
  },
262
  {
263
  "part": "group_post",
264
  "idx": 24,
265
+ "precision": "A_BF16_W_INT8"
266
  },
267
  {
268
  "part": "group_post",
269
  "idx": 25,
270
+ "precision": "A_BF16_W_INT8"
271
  },
272
  {
273
  "part": "group_post",
274
  "idx": 26,
275
+ "precision": "A_BF16_W_INT8"
276
  },
277
  {
278
  "part": "group_cache",
279
  "idx": 0,
280
+ "precision": "A_BF16_W_INT8"
281
  },
282
  {
283
  "part": "group_cache",
284
  "idx": 128,
285
+ "precision": "A_BF16_W_INT8"
286
  },
287
  {
288
  "part": "group_cache",
289
  "idx": 256,
290
+ "precision": "A_BF16_W_INT8"
291
  },
292
  {
293
  "part": "group_cache",
294
  "idx": 384,
295
+ "precision": "A_BF16_W_INT8"
296
  },
297
  {
298
  "part": "group_cache",
299
  "idx": 512,
300
+ "precision": "A_BF16_W_INT8"
301
  },
302
  {
303
  "part": "group_cache",
304
  "idx": 640,
305
+ "precision": "A_BF16_W_INT8"
306
  },
307
  {
308
  "part": "group_cache",
309
  "idx": 768,
310
+ "precision": "A_BF16_W_INT8"
311
  },
312
  {
313
  "part": "group_cache",
314
  "idx": 896,
315
+ "precision": "A_BF16_W_INT8"
316
  },
317
  {
318
  "part": "group_cache",
319
  "idx": 1024,
320
+ "precision": "A_BF16_W_INT8"
321
  },
322
  {
323
  "part": "group_cache",
324
  "idx": 1152,
325
+ "precision": "A_BF16_W_INT8"
326
  },
327
  {
328
  "part": "group_cache",
329
  "idx": 1280,
330
+ "precision": "A_BF16_W_INT8"
331
  },
332
  {
333
  "part": "group_cache",
334
  "idx": 1408,
335
+ "precision": "A_BF16_W_INT8"
336
  },
337
  {
338
  "part": "group_cache",
339
  "idx": 1536,
340
+ "precision": "A_BF16_W_INT8"
341
  },
342
  {
343
  "part": "group_cache",
344
  "idx": 1664,
345
+ "precision": "A_BF16_W_INT8"
346
  },
347
  {
348
  "part": "group_cache",
349
  "idx": 1792,
350
+ "precision": "A_BF16_W_INT8"
351
  },
352
  {
353
  "part": "group_cache",
354
  "idx": 1920,
355
+ "precision": "A_BF16_W_INT8"
356
  },
357
  {
358
  "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-3.2-3B-Instruct_language_n128_cache_token0_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cc7cf91d8b00fa25199b4f59a06cf10a727efcd01927b4153cde5a0af265198
3
- size 3416472
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca700b22e336c83e71d880148fc48790736e2aa79d25b1a25c9b91ace5b46297
3
+ size 3401432
elf_files/models--meta-llama--Llama-3.2-3B-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:db832a41ec987b93a05e744f4a4a2e8010ba9a4eefe0bb831025689612bdc333
3
- size 12117008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a46169a6ef8fccd0d039a5b0f9bdfb93f26a71d187492796be4b1ab90aaeab9
3
+ size 10845272
elf_files/models--meta-llama--Llama-3.2-3B-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:aab64711709a94a413709820fadc76cdee8520ff183a717dc765a4bf298d5eda
3
- size 24802248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5ef188745c39367a33ab9063e2b09fca4e11dea0c381b8818cddf868d35b119
3
+ size 13135256
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token1280_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:869beb962c1b53981f6eff6d2bb73df3b482c6079215c1edfd227eb59256f896
3
- size 18557320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f7de46dcae36af5daeaec2d934c045ee2136188870bfc0156b1cb367a275031
3
+ size 12327728
elf_files/models--meta-llama--Llama-3.2-3B-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:f7038f9fd20fd49180a509da77a73b4ff163a3043b966d53f6c06d440f3487d5
3
- size 3548848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ebb28ee3f4c51f24ecdceca2c3a863f0f62ca4a1565c420d55525614c6b2c5
3
+ size 4233104
elf_files/models--meta-llama--Llama-3.2-3B-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:dcd4f4b853edd384d58b7e9ad7c9a0116f7e9c6c9ee5f86fda64cb4fe7777409
3
- size 13150896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896cb3c3aae95b8e7ab7c1f74b902b7c9eb62eaf21a8a3fa48a958b575a3b9cc
3
+ size 15098336
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token1536_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:282553c8e06da07e99b592e6bdda256cf803800262c426b57991a9f8a3ebc4d6
3
- size 12214048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405fa5b6f5ce843d3f6419891b1140c44be8d533043a09536cb144aeb9ecae5a
3
+ size 12033840
elf_files/models--meta-llama--Llama-3.2-3B-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:e7c2b11ea80d07aab5df9b6e14b44f8c482c756abdb5780de6ce1287345c17c6
3
- size 24761864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de1cab87bdc81a223154d3ecbb303690087edaa41fb27049df94cb9265b4a1c
3
+ size 12084936
elf_files/models--meta-llama--Llama-3.2-3B-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:b7a0ff25730f3ed0b8e784a265b0cea166b08060233fdb93463b31b4508073a0
3
- size 22043496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1848620773150da324539516d61a425c74f08fe2ebdae20f0176d9f93c609c
3
+ size 13031456
elf_files/models--meta-llama--Llama-3.2-3B-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:e8c0b6301b61bab3594b1240772454561b361d5115130c242e65d18fbdcd5b0b
3
- size 15465568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f68808d78245db93cb412cf22ceabdf9df91707dac3280af7e237b6eee85ab
3
+ size 13259552
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token256_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37e3ee9f6718ce604807796612ffc41a1234b2c1a787e5c0cd043a05da86cbb2
3
- size 3933856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ba56b4e2ef804240fa93cc37da5d0193bd451c22f2b89cf3031a47a3ea99e9c
3
+ size 4396720
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token384_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:673c505346c162d9e9adaa05825ccedbebe84d2c0efb13cf7d86bb3a75cd1d36
3
- size 4238864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20bc01829749925f9eb22110a3fbf35236524a171132b7841303690d4de224e0
3
+ size 4621064
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token512_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95246069dcd64bc618c8597983f842f167986a70c6ec78c6ab61f4ec7a1c16d4
3
- size 6740760
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac8590821dbdb8ce3a9faff797fa4180bb57cb64e16545ce657437298411111f
3
+ size 5901152
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token640_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:826cd2e1623f7635955c24b973d980b357c71005d0bf7db3a99d47cee4d5a808
3
- size 6221152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d3b95e893a63f13b38645496a47df5a14e1b78d909634ee121dabd08f889ff5
3
+ size 5997512
elf_files/models--meta-llama--Llama-3.2-3B-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:bafd240c169ae9fa2c555d319132cca4ef030c2fe1bf60b525bcc29de17fcf5c
3
- size 9033224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f97a8933bafba66a4fe026ff39ac46427212672d1f9090c01918852d7bdd32e9
3
+ size 6072704
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_cache_token896_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:985e4651fab8632aa4cfbefc3013b59e68f1378330eb64d6d07021565e8f96cd
3
- size 8640680
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc8d79b37a359a6d6df883eb6f22e4eaf7566a9dbb73f9692a89db15accab2fb
3
+ size 7383576
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer0_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:386b495f68c8b1b07b934bbc4e284c72a187e6abc62a020bd86ca8177e29beb7
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89bb0d4f3b764e057e61c189a21c2d011d07160c66ef4513cb99ed391d882538
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer10_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bdf7f36c3eb457683fad82cda39476a47492927d0713f4c2613b8206d09233a
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe12defe5da30929f5b14abf21ada4dfe4801c6393a306274f657b4ca5ef9d0
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer11_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7080d6c88bcb8e8265df94b210e3a293d9a20440daf4d8b11e9de3cd2c1be01d
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c877069bef2789388b91bf6f93115493e3c0c8a34903e98572f5f9d9ff7cc689
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-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:a524af24380b37d83dd933139d0ab61902c9ef1602e0d2e3d4de51030084a5b7
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d98da92ff4256586df904d73d066564d85e24d45ba5659a3f4bb1e693a09139d
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer13_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48ff629c95f99e5f224bd670dc5f63f6c03d2c53261a2a670d687ebd8b20b472
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a855e8efaa8f1d7336306a604f1a68217b16409d5e652b18c83e1357e3ef4568
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-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:c6844439ff9df34e86df6bfe78da5831523e3e7c2bfd192b68a385ca4afee68d
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbfacc6c8746d483c117a5283cbb5d5ce64ebadaf75bc17f36663302e207ee56
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer15_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23c9d6ddb0f2a72df1f491eb3007b331dff2a9bc2b40e307dec818ddebfe75b5
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89e5a35fe6b214ee4e323b77142467f890cafcd7f19e4e9fe629bf439a2772db
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer16_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:647dcee9e256859a92a540e0f91327dcb38a5a2b52ca3012cf2666c73495c637
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b6727a850ec028597ad824043122d0071471dc9ec18cb653b53a47f61a5195
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer17_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:131ea259b9973d4b567272461b6b40c07a5dfe24dd329fdd56d3ecc43699b9e2
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b46df5861eea55437dae07b00452cc9a0c3c96dcceefbfa33e85b47946d0b3e
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-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:a0b56160b5718c82c9056f0c651db2485a2661fba2f817e8c9a87d8be574cb37
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06372bb3504f5ef095645b2f5c2c477f4b4c79d4447e22303541b7cae8253b3b
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer19_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03b2c8e5d42c721d432ec4452eba1effe28bec3ed1abb600f73b7f5a623a39d2
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75a855b5426a45f291592f11a3af059f54cc5417b8b8ee9b7a209dc8cb3f3893
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer1_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cb13102a1cb85ed42c3d09864167ba1ded551a453d74d376a6095d55f7d2d2f
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f17bb9d7dc55a8acdd9ad0a577bbd5091b1f97cd80d61c404148b8edb40a3d3
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer20_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d260601b3507a9a064d3cbb5cd6fa0700db1eee2959ca40b83c28b7fa685d48
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:986b0496a5ac6e0f7137d1b92b3cd88b817167f2891b771a26b0cf69cd2e0f9e
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer21_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:658ccb8b5e575e98608f491c7d1dfdd0e3c821deca0f39b3d495913124f61781
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503cbf9435c4c674855ecba6a158fe70dbb82f93bf908abb80e25274aa77c867
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer22_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82a0fde8d6655f18ecbc5c834c05f8010f9c8c85a24078118adde6410cf5bba1
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f54c127c779643907294d47887a26ada15aa14eece2ad7008155e94c87bc1c49
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-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:b5a6b44def88d0fa02f9c32b3bdfb38e07cc7ddf9032d8967178c59ef79532ee
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db38a4c71ceede23f9ef22c02ef34f1afefe09398f03a8b0c1a1f2bcd53367c0
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-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:dd59a2437534585cf6c60ad14a0a37249ea0b2e3c691a3917bbc514466dc52e2
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ce53f2e040c14c0e87aa92d227057e5a9825478ea5ed99bdb597aea5a9c944
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer25_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bbce6425fd7d9d7a72338132bbebe97530a861c2988060ead26428065191abb
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e5d0aafb478ae9a08979c1305eb0a7e0929a84714f710b59f3b0e809e77a19a
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-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:d433e27a321a0156c44081a7af43285b6a33e2a688ef88967b846117511bd47a
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4687c78ab9fd4a075712d097ed63d4bfbf9a7504f3a43e4d2eb4fde1eac2e5b
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer2_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34e569bce07cd81ef54b1bf627b2ecc75b4c7f245198011acff9319245e94749
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cda2ae33cfb044af3071daf7dba0daeb0b626482e2dd8eb761d294317764ba6
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer3_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7539d76cde202f7346b3c0ebf55d408d68c9b00729aae8ead3faf0bde7f4ff41
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e14ddbe272e944c4a9983752cb998e5659b71d0e032875feca4b77afe595579
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer4_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:551fbef0e897672e18bb0e7462401f76aae4e69fb432de6e2737b74b43f9fb1a
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b9d966a14b28ee545f25b52a16f3c74a472ebe6bded9f313a4e2186ee482564
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-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:af3fc9a0e17dd4476cd9efe062f8a39b96e83b1c145b7bec88809292bc6388cd
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:242a872951efdcb3c4ded087d180a4ab78a1dbb05a852ff0bc3660cbc681923a
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer6_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cbaac4cc1906da6def30c928db966632f23ad7d9e8b2c441fabc627d69d3104
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f485ccfd524293afdfc88d8f71c8dcd299aba0733a6ea474d48d26199ff763a0
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer7_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e54df77cdc5060c4722d941510358f2da444976794b8b8ca9d75a6d5cbe8f54
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dd6b6a9054e367b7860a17fb23cccf8bd7b6bbe23b88b86bad97b8218622841
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-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:d4a0f55d41ecc2306ece68b917318fecb0626c9344b2e510459f8354f8cd78c5
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117c81f47e8281d330636d2136930e016a37da02e33a4084a40c2b8a57e4bf05
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_post_layer9_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5471f1402da01962aa28c963467931ba0a801b8adbc164cb229ebfaac2e4aea0
3
- size 112493256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59a0eabd082e0cc3459ace47288f654850ea093194e970d034ac42849395200a
3
+ size 97409136
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_pre_layer0_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97b14da070c40de6de2ad4edbaa97184bbb1bb8c2974662e6cf321ee7a51fa10
3
- size 21633608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15ef21defe8ecd945fdfff0a60b70c319d2d975a1083f6ce12848a025b96fb80
3
+ size 21807424
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_pre_layer10_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6886e86e7fe352282708af41ae70200dd078dc386d5dd71877be2a776ca4acb2
3
- size 21633608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a96ab9b78c2d0bbbb5eeeb3083469fd2aff5ee50477a1d47288aaf6467d241ec
3
+ size 21807424
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_pre_layer11_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216d12dbf134d126bef2c030c53eba9e4f371ed7c64b769299b8e56687c2b6b0
3
- size 21633608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3978d4768b3d95f57f48c8a717f2565a627036ad8ca4e1da309fb6fe26233e76
3
+ size 21807424
elf_files/models--meta-llama--Llama-3.2-3B-Instruct_language_n128_pre_layer12_stage1_mla.elf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4bf962d2e560fff37136b62d46015049221985aa25c2548a715316d395dcc86a
3
- size 21633608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88336f6ed59be62f94df6612a0dc2758c11a23c7f8358358346506a947a492f3
3
+ size 21807424