| { |
| "attention": "vanilla", |
| "cases": "3fe1b15858329766a4fe532dad9d3aa1fb49f712b7b9f7443eb5049800b227ee", |
| "ffn": "reference", |
| "model_sha256": "7b2d8777040f05d8e0849acac4e45013b2de3d72145c363cd22825e80115c515", |
| "precision": "FP32 base masters plus FP32 trained deltas", |
| "prompt_truncation": false, |
| "repetition_penalty": 1, |
| "scoring": { |
| "pretraining/chat_benchmark/panel.py": "70d78840147614727a34a775f669f9316c8d589721d41fdf2dd8c98deb2475bd", |
| "pretraining/chat_benchmark/scoring.py": "e63a8715c302e2b59b0fadc3598e912d3f695fb9352b541e33dba3b046017c54", |
| "pretraining/scripts/benchmark_best.py": "f3835c8cb0bdf580e4142a57ac3724c474dcc1d44aa01dbbd805c989a587c7c7", |
| "pretraining/scripts/benchmark_ifeval.py": "10ae9d2c49236c377d6e9952674b14289f5f92c310c29cbe592a40c98a14c752", |
| "pretraining/sft/data.py": "5c558b0cfd4d2061af144c3f295b7bec31d92cb4b0fb605f702972c373e2d1e8", |
| "pretraining/sft/evaluate.py": "80624551512112850145ccb57d6435d7a1bae86d0b95f8f52d56b8cb6f102a76", |
| "pretraining/sml_v1/model.py": "1eee6f8afe78767ff6b9c604ccf2328c98b24bc94dbad6291a0ad699dd7345fe", |
| "pretraining/sml_v1/tokenization.py": "254e1f5d60cc4498a9f1209955752db28b91839f48d3121d674f3f5ac42e52e5" |
| }, |
| "system_prompt": null, |
| "temperature": 0, |
| "weight_provenance": { |
| "precision": "FP32 pretrained masters plus FP32 LoRA and tied chat-token deltas", |
| "resume": "Use the enclosing adapter bundle; this is an inference export", |
| "trainable_parameters": 3785856 |
| } |
| } |
|
|
