an example to fine-tuning a Language Learning Model (LLM) from data preparation to deployment.
Python
3
64 commits
updated Nov 5, 2024
Welcome to the Custom LLM Finetuning Handbook, an example to fine-tuning a Language Learning Model (LLM) from data preparation to deployment. This handbook covers various aspects including data preparation, supervised fine-tuning (SFT), direct preference optimization (DPO), evaluation on common benchmark, and deployment using vLLM with an intuitive user interface.
We have uploaded the trained checkpoint:
Data preparation is the most crucial part. Here are the steps involved:
The collecting data is placed under https://huggingface.co/datasets/lu-vae/cciip-gpt-dataset
For SFT, you can use either LoRA (Low-Rank Adaptation) or full model fine-tuning. The primary repository for this process is https://github.com/LZY-the-boys/axolotl clone it and customize the yaml configuration file.
Multi-modal Training you can visit this: https://github.com/OpenAccess-AI-Collective/axolotl/tree/llava-train
LoRA-example you can vist: https://github.com/Facico/Chinese-Vicuna
Dependency:
DPO is a method used to optimize the model's performance based on human preferences. The repositories involved are:
Leaderboard:
Leaderboard: TODO
Merging-Kit: https://github.com/arcee-ai/mergekit Twin-Merging: https://github.com/LZY-the-boys/Twin-Merging
The final step involves deploying your fine-tuned LLM using vLLM, ensuring it is accessible through a user-friendly interface. This section will guide you through the deployment process, ensuring your model is ready for use in real-world applications.
vllm deploy: https://github.com/LZY-the-boys/vllm
UI:
an example to fine-tuning a Language Learning Model (LLM) from data preparation to deployment.
Python
3
64 commits
updated Nov 5, 2024
Welcome to the Custom LLM Finetuning Handbook, an example to fine-tuning a Language Learning Model (LLM) from data preparation to deployment. This handbook covers various aspects including data preparation, supervised fine-tuning (SFT), direct preference optimization (DPO), evaluation on common benchmark, and deployment using vLLM with an intuitive user interface.
We have uploaded the trained checkpoint:
Data preparation is the most crucial part. Here are the steps involved:
The collecting data is placed under https://huggingface.co/datasets/lu-vae/cciip-gpt-dataset
For SFT, you can use either LoRA (Low-Rank Adaptation) or full model fine-tuning. The primary repository for this process is https://github.com/LZY-the-boys/axolotl clone it and customize the yaml configuration file.
Multi-modal Training you can visit this: https://github.com/OpenAccess-AI-Collective/axolotl/tree/llava-train
LoRA-example you can vist: https://github.com/Facico/Chinese-Vicuna
Dependency:
DPO is a method used to optimize the model's performance based on human preferences. The repositories involved are:
Leaderboard:
Leaderboard: TODO
Merging-Kit: https://github.com/arcee-ai/mergekit Twin-Merging: https://github.com/LZY-the-boys/Twin-Merging
The final step involves deploying your fine-tuned LLM using vLLM, ensuring it is accessible through a user-friendly interface. This section will guide you through the deployment process, ensuring your model is ready for use in real-world applications.
vllm deploy: https://github.com/LZY-the-boys/vllm
UI:
