Download rl_agent_config.json from Dat2508/rex: direct link, hf CLI and curl.
- Browser
- Download file 812 Bytes
-
https://huggingface.co/Dat2508/rex/resolve/main/rl_agent_config.json
- Command line
-
hf download hf://Dat2508/rex/rl_agent_config.json
-
curl -L -o rl_agent_config.json https://huggingface.co/Dat2508/rex/resolve/main/rl_agent_config.json
812 Bytes
| { | |
| "encoder": "answerdotai/ModernBERT-large", | |
| "head_layers": 2, | |
| "max_len": 512, | |
| "head_max_len": 128, | |
| "max_prefixes": 6, | |
| "act_costs": { | |
| "escalate": 0.5 | |
| }, | |
| "cost_wrong_act": 3.0, | |
| "amp_dtype": "bf16", | |
| "model_name": "requin-security-decision-engine", | |
| "temperature": [ | |
| 1.5, | |
| 1.2, | |
| 1.0 | |
| ], | |
| "temperature_by_options": { | |
| "choice:3-5": 1.7601518630981445, | |
| "choice:6-10": 1.0000158548355103, | |
| "score:3-5": 1.2514300346374512, | |
| "noul:2": 1.983399510383606, | |
| "choice:11+": 0.10058280825614929, | |
| "choice:2": 1.9063563346862793 | |
| }, | |
| "training": { | |
| "updates": 7313, | |
| "epochs_completed": 1, | |
| "hours": 1.96, | |
| "world_size": 1, | |
| "fine_tuned_from_checkpoint": true | |
| }, | |
| "gradient_checkpointing": true, | |
| "max_tokens_per_batch": 4096, | |
| "fine_tuned": true | |
| } |