Files
Llama-3.2-1B-MathCodeInstru…/assets/speed_results.json
ModelHub XC 7c84d9a138 初始化项目,由ModelHub XC社区提供模型
Model: OliverSundaram/Llama-3.2-1B-MathCodeInstruct-20k
Source: Original Platform
2026-10-29 07:56:16 +08:00

92 lines
2.6 KiB
JSON

{
"config": {
"prompt": "Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May? Solve step by step.",
"tokens_per_run": 256,
"rounds": 3,
"interleaved": true,
"dtype": "bfloat16",
"greedy": true,
"device": "NVIDIA GeForce RTX 4060",
"torch": "2.11.0+cu128"
},
"models": {
"base": {
"model_path": "unsloth/Llama-3.2-1B",
"decode_tok_s": 40.59,
"decode_tok_s_min": 39.28,
"decode_tok_s_max": 40.62,
"end_to_end_tok_s": 40.56,
"prefill_ms": 29.3,
"prompt_tokens": 44,
"generated_tokens": 256,
"rounds": [
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.0321,
"total_s": 6.5236,
"decode_tok_s": 39.28,
"end_to_end_tok_s": 39.24,
"gpu": "51C / 2775MHz"
},
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.0293,
"total_s": 6.307,
"decode_tok_s": 40.62,
"end_to_end_tok_s": 40.59,
"gpu": "58C / 2775MHz"
},
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.0293,
"total_s": 6.3119,
"decode_tok_s": 40.59,
"end_to_end_tok_s": 40.56,
"gpu": "51C / 2775MHz"
}
]
},
"20k": {
"model_path": "Llama-3.2-1B-MathCodeInstruct-20k/outputs/llama-3.2-1b-20k",
"decode_tok_s": 40.63,
"decode_tok_s_min": 40.61,
"decode_tok_s_max": 40.67,
"end_to_end_tok_s": 40.6,
"prefill_ms": 29.7,
"prompt_tokens": 44,
"generated_tokens": 256,
"rounds": [
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.0295,
"total_s": 6.3088,
"decode_tok_s": 40.61,
"end_to_end_tok_s": 40.58,
"gpu": "57C / 2775MHz"
},
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.0308,
"total_s": 6.3005,
"decode_tok_s": 40.67,
"end_to_end_tok_s": 40.63,
"gpu": "51C / 2775MHz"
},
{
"prompt_tokens": 44,
"generated_tokens": 256,
"prefill_s": 0.0297,
"total_s": 6.3062,
"decode_tok_s": 40.63,
"end_to_end_tok_s": 40.6,
"gpu": "52C / 2775MHz"
}
]
}
}
}