codellama
/

CodeLlama-7b-hf

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

CodeLlama-7b-hf / generation_config.json

loubnabnl's picture

loubnabnl HF staff

use 6 shards instead of 2

be52f4a about 1 year ago

116 Bytes

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