Qwen3-VL-8B-Instruct-NVFP4-FP8-Dynamic / generation_config.json
JEILDLWLRMA's picture
v3.1: Add quantization_config to config.json for proper tensor format detection
5e5a9e3 verified
raw
history blame contribute delete
217 Bytes
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "5.0.0.dev0"
}