HeyMiku
/

Intent-Classifier-4B

Text Generation

Model card Files Files and versions

Intent-Classifier-4B / generation_config.json

HeyMiku's picture

Replace MLX 4-bit with BF16 merged model (SFT best@6k, val loss 0.015). Compatible with vLLM/transformers.

7588fa9 verified 4 days ago

history blame contribute delete

115 Bytes

	{
	"_from_model_config": true,
	"eos_token_id": 248044,
	"transformers_version": "5.5.0",
	"use_cache": true
	}