Text Generation
Transformers
Safetensors
English
llama
text-generation-inference
4-bit precision
gptq
wizard-mega-13B-GPTQ / generation_config.json
TheBloke's picture
First upload of GPTQ model.
37176e6
raw
history blame
137 Bytes
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"transformers_version": "4.30.0.dev0"
}