OPEA
/

Safetensors
qwen2_vl
4-bit precision
intel/auto-round
Qwen2-VL-72B-Instruct-int4-sym-inc / generation_config.json
weiweiz1's picture
auto_gptq format
e67cae7
raw
history blame contribute delete
222 Bytes
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"top_k": 1,
"top_p": 0.001,
"transformers_version": "4.47.0"
}