Text Generation
Transformers
Safetensors
qwen3_moe
conversational
8-bit precision
compressed-tensors
Qwen3-Coder-30B-A3B-Instruct-NVFP4 / generation_config.json
ig1sa's picture
Upload folder using huggingface_hub
c9f609c verified
raw
history blame contribute delete
217 Bytes
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"repetition_penalty": 1.05,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8,
"transformers_version": "4.56.2"
}