my-alpaca

Reproduce alpaca. A case of the trained model:

Relate Repositories

• my-llm all about large language models
• try-large-models try large models
• multi-turn-alpaca train alpaca with multi-turn dialogue datasets
• alpaca-rlhf train multi-turn alpaca with RLHF (Reinforcement Learning with Human Feedback)

Step by Step

• filetune
  • nohup sh run.sh my_alpaca/autodl/finetune.py > autodl.log 2>&1 &
• inference_llama_gradio
  • sh run.sh my_alpaca/autodl/inference_llama_gradio.py
• inference_alpaca_lora_gradio
  • sh run.sh my_alpaca/autodl/inference_alpaca_lora_gradio.py