Text Generation
Transformers
Safetensors
English
German
mistral
conversational
text-generation-inference
4-bit precision
gptq
Leo-Mistral-Hessianai-7B-Chat-GPTQ / generation_config.json
TheBloke's picture
GPTQ model commit
64d996e
raw history blame
No virus
111 Bytes
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.34.0"
}