Qwen3-0.6B-NVFP4 / generation_config.json
llmat's picture
Add NVFP4 quantized model for Qwen/Qwen3-0.6B.
d83e6a5 verified
raw
history blame
214 Bytes
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "4.55.4"
}