File size: 3,784 Bytes
e476358 | 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 | {
"all_floating_tensors_finite": true,
"assets_sha256": {
"chat_template.jinja": "c3cf9e34abf4f9e36c2d72165aa9c132d3e2a725b6c2586aaa3a8af9d7a81041",
"generation_config.json": "e70c136c1b78ddc1fb0905bac8e733a4dc448d4f852a5dd75143fffc70be550e",
"merges.txt": "a9d356d7bdf1ef4949e3e748e95b8e10ad9d4e2e838eddc38a0a7b6b94d1db8d",
"preprocessor_config.json": "27225450ac9c6529872ee1924fcb0962ff5634834f817040f444118116f4e516",
"tokenizer.json": "0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3",
"tokenizer_config.json": "b11349aafa7cdc6a320767cf7ceb29ed82f7eda5d65e8e0819e76f0ce947bf27",
"video_preprocessor_config.json": "7768af27c1fafa9cc9011c1dc20067e03f8915e03b63504550e11d5066986d13",
"vocab.json": "ce99b4cb2983d118806ce0a8b777a35b093e2000a503ebde25853284c9dfa003"
},
"categories": {
"MTP": 15,
"text": 851,
"vision": 333
},
"chat_templates": [
{
"options": {
"enable_thinking": false
},
"rendered": "<|im_start|>user\nSay hello.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n"
},
{
"options": {
"reasoning_effort": "low"
},
"rendered": "<|im_start|>system\nReasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.<|im_end|>\n<|im_start|>user\nSay hello.<|im_end|>\n<|im_start|>assistant\n<think>\n"
},
{
"options": {
"reasoning_effort": "xhigh"
},
"rendered": "<|im_start|>system\nReasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.<|im_end|>\n<|im_start|>user\nSay hello.<|im_end|>\n<|im_start|>assistant\n<think>\n"
}
],
"exact_unquantized_tensors": 609,
"generation": {
"elapsed_seconds": 495.4394222159999,
"finish_reason": "stop",
"prompt": "<|im_start|>user\nReply with exactly: Hello from Swift.<|im_end|>\n<|im_start|>assistant\n<think>\n\n</think>\n\n",
"prompt_tokens_per_second": 0.04886516458777248,
"text": "Hello from Swift.",
"token_ids": [
9419,
494,
22929,
13,
248046
],
"tokens": 5,
"tokens_per_second": 0.05894060179705689
},
"ignored_tensors": 0,
"inference_floating_dtype": "float32, CPU runtime only; stored floating tensors remain BF16",
"load_memory_bytes": 19281804392,
"load_seconds": 3.1353140849996635,
"mapped_source_tensors": 1199,
"mtp": {
"path": "Explicit MTP step with real text hidden states and shared LM head; speculative generation is not integrated",
"shape": [
1,
1,
248320
],
"status": "PASS"
},
"native_bf16_cpu_inference": "Aborted after reproducing incorrect accumulation in the official Linux BF16 quantized matmul. See cpu-quantized-matmul-diagnostic.json.",
"process_peak_rss_bytes": 24964259840,
"processor": "Qwen3VLProcessor",
"quantization": {
"bits": 5,
"group_size": 64,
"mode": "affine"
},
"recorded_at": "2026-09-22T12:17:07.052752+00:00",
"saved_tensors": 2379,
"source_repo": "ukisai/Swift-1.5-Qwen3.8-27b",
"source_revision": "5ad04445d2686f525e9fbe5c077e6fa0c7df4200",
"source_shard_bytes": 55563006776,
"source_shards": 18,
"source_tensors": 1199,
"status": "PASS",
"tokenizer": "Qwen2Tokenizer",
"total_validation_seconds": 609.2779944080003,
"unexplained_tensors": 0,
"vision": {
"grid": [
[
1,
16,
16
]
],
"path": "Vision encoder only; image/video insertion and multimodal text generation are not implemented",
"shape": [
64,
5120
],
"status": "PASS"
}
}
|