alinourian / Fine-tuning-Mistral-7b-QA

Fine tuning Mistral-7b with PEFT(Parameter Efficient Fine-Tuning) and LoRA(Low-Rank Adaptation) on Puffin Dataset(multi-turn conversations between GPT-4 and real humans)

Geek Repo

Github PK Tool

fine-tuning gpt-4 hugging-face large-language-models llm lora low-rank-adaptation mistral-7b multi-turn-dialogue parameter-efficient-fine-tuning peft puffin wandb

Fine-tuning-Mistral-7b-QA

Fine tuning Mistral-7b with PEFT(Parameter Efficient Fine-Tuning) and LoRA(Low-Rank Adaptation) on Puffin Dataset(multi-turn conversations between GPT-4 and real humans) with wandb

About

Fine tuning Mistral-7b with PEFT(Parameter Efficient Fine-Tuning) and LoRA(Low-Rank Adaptation) on Puffin Dataset(multi-turn conversations between GPT-4 and real humans)

fine-tuning gpt-4 hugging-face large-language-models llm lora low-rank-adaptation mistral-7b multi-turn-dialogue parameter-efficient-fine-tuning peft puffin wandb

Languages

Language:Jupyter Notebook 100.0%