Text Generation
Transformers
llama
Inference Endpoints
ct2-int8-open-llama-7b-v2 / generation_config.json
Jamie@TitanML
Upload folder using huggingface_hub
a306029
raw
history blame contribute delete
132 Bytes
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.30.1"
}