laya:421m-typed-decisions-mlx-fp16

2 5 days ago

Laya is a 421M decision model from Convai Innovations, fine-tuned from ModernBERT-large.

decision
... /
json
ebf0cd524d92 · 847B
{
"encoder": "answerdotai/ModernBERT-large",
"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": "laya-typed-decisions",
"temperature": [
1.0148024559020996,
1.0374259948730469,
1.0575125217437744
],
"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
}