Mistral-Small-24B-Instruct-2501-NVFP4 / generation_config.json
llmat's picture
Add NVFP4 quantized model (llmcompressor oneshot).
a77c13c verified
raw
history blame contribute delete
155 Bytes
{
"_from_model_config": true,
"bos_token_id": 1,
"do_sample": true,
"eos_token_id": 2,
"temperature": 0.15,
"transformers_version": "4.55.4"
}