javiergtzr
/

CodeLlama-7b-Instruct-hf-4bit

Text Generation

4-bit precision

Model card Files Files and versions

CodeLlama-7b-Instruct-hf-4bit / generation_config.json

javiergtzr's picture

Add files using upload-large-folder tool

117bdc1 verified 9 months ago

history blame contribute delete

116 Bytes

	{
	"_from_model_config": true,
	"bos_token_id": 1,
	"eos_token_id": 2,
	"transformers_version": "4.33.0.dev0"
	}