Download rl_agent_config.json from Dipto084/safe_laya: direct link, hf CLI and curl.
- Browser
- Download file 762 Bytes
-
https://huggingface.co/Dipto084/safe_laya/resolve/main/rl_agent_config.json
- Command line
-
hf download hf://Dipto084/safe_laya/rl_agent_config.json
-
curl -L -o rl_agent_config.json https://huggingface.co/Dipto084/safe_laya/resolve/main/rl_agent_config.json
762 Bytes
| { | |
| "encoder": "answerdotai/ModernBERT-large", | |
| "head_layers": 2, | |
| "max_len": 8192, | |
| "head_max_len": 256, | |
| "max_prefixes": 6, | |
| "act_costs": { | |
| "escalate": 0.5 | |
| }, | |
| "cost_wrong_act": 3.0, | |
| "amp_dtype": "bf16", | |
| "model_name": "laya-typed-decisions", | |
| "temperature": [ | |
| 2.67520809173584, | |
| 2.67520809173584, | |
| 2.67520809173584 | |
| ], | |
| "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, | |
| "finetune": { | |
| "task": "TRACE ALLOW/DECLINE", | |
| "items": 5334, | |
| "epochs": 4, | |
| "ce_weight": 1.0, | |
| "rl_weight": 0.0, | |
| "max_len": 8192, | |
| "group_size": 4 | |
| } | |
| } |