| { |
| "source": "Agnes-AI/Agnes-3.0-Flash", |
| "source_revision": "24f712ce59379b54c4a141d2708c35daf5ff613b", |
| "target": "ProCreations/Agnes-3.0-Flash-NVFP4", |
| "status": "build_failed", |
| "code_revision": "fd26a7a3f427396175c3c6421b3a106cee45570f", |
| "modelopt_revision": "5cae3940402f1ced98069a666b0bec72ec8b33b5", |
| "quantization": { |
| "method": "plain NVFP4 max", |
| "training": false, |
| "calibration_examples": 0, |
| "calibration_tokens": 0, |
| "calibration_forward_calls": 0, |
| "activation_global_scale": 1.0, |
| "block_size": 16, |
| "activation_block_scales": "dynamic E4M3", |
| "kv_cache_quantized": false |
| }, |
| "folding": { |
| "main_width": 17408, |
| "parallel_width": 2048, |
| "folded_width": 19456, |
| "gate_up_dimension": 0, |
| "down_dimension": 1, |
| "layers": 72, |
| "reason": "Match the upstream SGLang BF16 loader before quantization" |
| }, |
| "evaluation": { |
| "status": "pending" |
| }, |
| "versions": { |
| "torch": "2.13.0", |
| "transformers": "5.12.1", |
| "nvidia-modelopt": "0.0.0", |
| "accelerate": "1.12.0" |
| }, |
| "hardware": [ |
| "NVIDIA H200" |
| ] |
| } |
|
|
