Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.
11.57k
stars
1.64k
forks
source link
Recommendations to save, store & re-use results? #598
Thank you for this notebook. It would be helpful to add suggested code for storing and retrieving text embeds with Faiss, and also code for storing and retrieving the summary index somewhere. Storage and retrieval are critical for real-world use, even locally. People don't want to re-index everything every time they have a question.
🚀 The feature, motivation and pitch
Thank you for this notebook. It would be helpful to add suggested code for storing and retrieving text embeds with Faiss, and also code for storing and retrieving the summary index somewhere. Storage and retrieval are critical for real-world use, even locally. People don't want to re-index everything every time they have a question.
Alternatives
No response
Additional context
No response