Text Generation
Transformers
Safetensors
English
mistral
text-generation-inference
4-bit precision
gptq
dolphin-2.6-mistral-7B-dpo-laser-GPTQ / generation_config.json
TheBloke's picture
GPTQ model commit
2d1ee7d
raw history blame
No virus
111 Bytes
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.36.2"
}