code-oracle-laya-421m / base-164m /rl_agent_config.json
wxsys's picture
Add lightweight ModernBERT-base 164M model variant in BF16 (~312MB)
603a3e0 verified
Raw History Blame Contribute Delete
447 Bytes
{
"encoder": "answerdotai/ModernBERT-base",
"head_layers": 2,
"max_len": 1024,
"head_max_len": 256,
"max_prefixes": 6,
"act_costs": {
"escalate": 0.5
},
"cost_wrong_act": 3.0,
"amp_dtype": "bf16",
"model_name": "code-oracle-laya-modernbert-base",
"temperature": [
1.0,
1.0,
1.0
],
"temperature_by_options": {
"choice:2": 1.9,
"score:3-5": 1.25
},
"dataset_samples": 2400,
"accuracy": 0.995
}