File size: 6,590 Bytes
8789139 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 | {
"model_id": "nvidia/Qwen3.8-27B-NVFP4",
"revision": "482ca0f3832238542f8f5295dde86b5f22711d80",
"status": "complete",
"artifact": "/mnt/storage/flare/release-references/reference.safetensors",
"torch": "2.14.1+cu130",
"transformers": "5.21.0.dev0",
"device": "cuda:0",
"config_sha256": "71fa01bb64de20971045cd82a82c0ebb25a54e1b0a3f09ef23cf5479e9c54df8",
"index_sha256": "7aa103a2582b7d26631988de33dea19e8a308ee9c239e8e14feb374af30905e2",
"hf_model_source_sha256": "b4b17fe08d8d54da34a0fce78639666279ae7fd0a9e4ec06fce6602774707ca3",
"checkpoint_files": {
"config.json": {
"revision": "482ca0f3832238542f8f5295dde86b5f22711d80",
"etag": "da0edbc058d6042ec194d2b2b32d387cd03aed89"
},
"model-00001-of-00003.safetensors": {
"revision": "482ca0f3832238542f8f5295dde86b5f22711d80",
"etag": "7d0fd155118901373eb0fd13ed3aae68f95be747bc205be72ebc41739c25ee80"
},
"model-00002-of-00003.safetensors": {
"revision": "482ca0f3832238542f8f5295dde86b5f22711d80",
"etag": "98a7e9486baa860c792c9463a770cb9d017696bdd17606300a5b9334149f4c27"
},
"model-00003-of-00003.safetensors": {
"revision": "482ca0f3832238542f8f5295dde86b5f22711d80",
"etag": "0506ad35dc21469708e7813bd76c592cef08bd0317b4a1fe899745ebe2435271"
},
"model.safetensors.index.json": {
"revision": "482ca0f3832238542f8f5295dde86b5f22711d80",
"etag": "146d8eb292e9ffbfe4865b665069784720e57662"
},
"tokenizer.json": {
"revision": "482ca0f3832238542f8f5295dde86b5f22711d80",
"etag": "0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3"
},
"tokenizer_config.json": {
"revision": "482ca0f3832238542f8f5295dde86b5f22711d80",
"etag": "77053000a771610a7c97f7b1f06fdb03aa357128"
}
},
"options": {
"root": "/mnt/storage/flare/release-references",
"checkpoint": "/mnt/storage/flare/checkpoint",
"device": "cuda:0",
"prompt_tokens": 32,
"new_tokens": 16,
"prompt_batch_size": 3,
"head_tile": 2048,
"threads": 30
},
"prompts": [
{
"index": 0,
"source_text": "A careful scientist measures the temperature of a sealed container every minute. The first readings are twenty, twenty two, twenty four, and twenty six degrees. Explain the pattern and predict the next reading using the available observations.",
"prompt_text": "A careful scientist measures the temperature of a sealed container every minute. The first readings are twenty, twenty two, twenty four, and twenty six degrees. Explain the",
"prompt_ids": [
32,
16097,
26578,
10633,
279,
9039,
314,
264,
18473,
5303,
1396,
9104,
13,
561,
1118,
37780,
513,
16570,
11,
16570,
1330,
11,
16570,
2943,
11,
321,
16570,
4590,
11995,
13,
79091,
279
],
"generated_ids": [
5215,
303,
279,
795,
321,
6805,
279,
1727,
1330,
37780,
13,
271,
760,
5215,
303,
279
],
"generated_text": " pattern in the data and predict the next two readings.\n\nThe pattern in the",
"eos_positions": []
},
{
"index": 1,
"source_text": "Write a clear explanation of why the sky often appears blue during the day and why a sunset can look orange or red. Begin with the way sunlight interacts with the small particles and molecules in Earth's atmosphere.",
"prompt_text": "Write a clear explanation of why the sky often appears blue during the day and why a sunset can look orange or red. Begin with the way sunlight interacts with the",
"prompt_ids": [
7734,
264,
2708,
15673,
314,
3069,
279,
12515,
3428,
7701,
6105,
2261,
279,
1834,
321,
3069,
264,
41564,
628,
1353,
18016,
466,
2438,
13,
18037,
440,
279,
1560,
37728,
80291,
440,
279
],
"generated_ids": [
4860,
1752,
1472,
279,
16078,
506,
41564,
13,
271,
248068,
198,
760,
1156,
6587,
264,
2708
],
"generated_text": " longer path through the atmosphere at sunset.\n\n<think>\nThe user wants a clear",
"eos_positions": []
},
{
"index": 2,
"source_text": "A Python function receives a list of integers and returns the sum of the even numbers without changing the original list. Describe a simple implementation and explain how it behaves when the input list is empty or contains negative numbers.",
"prompt_text": "A Python function receives a list of integers and returns the sum of the even numbers without changing the original list. Describe a simple implementation and explain how it behaves when",
"prompt_ids": [
32,
12654,
709,
20539,
264,
1103,
314,
24959,
321,
4523,
279,
2542,
314,
279,
1442,
4947,
1973,
9722,
279,
3889,
1103,
13,
58737,
264,
4145,
7873,
321,
10033,
1204,
424,
70573,
948
],
"generated_ids": [
279,
1879,
1103,
5435,
874,
1442,
4947,
13,
271,
16,
13,
2972,
3886,
264,
491,
1103
],
"generated_text": " the input list contains no even numbers.\n\n1. **Create a new list",
"eos_positions": []
}
],
"stop_on_eos": false,
"elapsed_seconds": 101.08311609900557,
"comparison": "Teacher-force prompt_ids followed by generated_ids[:-1] in the candidate. Compare all prefill_logits and decode_logits at identical positions. Report KLD(reference||candidate), top-1 agreement, and separate independent greedy continuations; do not silently loosen bounds.",
"device_name": "NVIDIA RTX PRO 6000 Blackwell Workstation Edition",
"peak_allocated_bytes": 20204385792,
"peak_reserved_bytes": 20575158272
}
|