OPEA
/

Safetensors
qwen2
4-bit precision
gptq
Qwen2-7B-int4-sym-inc / generation_config.json
n1ck-guo's picture
remove config git lfs
8262a35
raw
history blame contribute delete
117 Bytes
{
"bos_token_id": 151643,
"eos_token_id": 151643,
"max_new_tokens": 2048,
"transformers_version": "4.44.2"
}