mirror of
https://github.com/hiyouga/LLaMA-Factory.git
synced 2025-11-08 22:34:46 +08:00
11 lines
400 B
YAML
11 lines
400 B
YAML
model_name_or_path: deepseek-ai/DeepSeek-V2-Lite
|
|
adapter_name_or_path: saves/Kllama_deepseekV2
|
|
template: deepseek
|
|
infer_backend: ktransformers # choices: [huggingface, vllm, sglang, ktransformers]
|
|
trust_remote_code: true
|
|
|
|
use_kt: true # use KTransformers as LoRA sft backend to inference
|
|
kt_optimize_rule: examples/kt_optimize_rules/DeepSeek-V2-Lite-Chat-sft-amx.yaml
|
|
cpu_infer: 32
|
|
chunk_size: 8192
|