Text Generation
Transformers
Safetensors
Japanese
English
mistral
conversational
text-generation-inference
4-bit precision
gptq
shisa-7B-v1-GPTQ / generation_config.json
TheBloke's picture
GPTQ model commit
ae1dcfc
raw history blame
No virus
133 Bytes
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.35.1",
"use_cache": false
}