rwitz
/

cat0.1

Text Generation

4-bit precision

Model card Files Files and versions Community

cat0.1 / generation_config.json

rwitz's picture

Merge LoRA with base model using 4-bit quantization and upload to HF

8826122 24 days ago

history blame contribute delete

121 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 128000,
	"eos_token_id": 128001,
	"transformers_version": "4.45.2"
	}