LLaMA-Factory / examples /merge_lora /llama3_gptq.yaml
ferid197's picture
Upload folder using huggingface_hub
e81015c verified
raw
history blame contribute delete
311 Bytes
### model
model_name_or_path: meta-llama/Meta-Llama-3-8B-Instruct
template: llama3
trust_remote_code: true
### export
export_dir: output/llama3_gptq
export_quantization_bit: 4
export_quantization_dataset: data/c4_demo.jsonl
export_size: 5
export_device: cpu # choices: [cpu, auto]
export_legacy_format: false