Text Generation
Transformers
Safetensors
English
llama
goliath
deutsch
llama2
discoresearch
text-generation-inference
4-bit precision
gptq
DiscoLM-120b-GPTQ / generation_config.json
TheBloke's picture
Add GPTQ sharded
d7a8e6b
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.35.2"
}