run-llama / finetune-embedding

Fine-Tuning Embedding for RAG with Synthetic Data
456 stars 65 forks source link

Sample Data missing #3

Open vasutech opened 1 year ago

vasutech commented 1 year ago

ValueError: File ../llama_index/docs/examples/data/10k/lyft_2021.pdf does not exist. Can you please link to the data required.

go-noah commented 1 year ago

https://github.com/jerryjliu/llama_index/blob/main/docs/examples/data/10k/lyft_2021.pdf

BadrinathMJ commented 11 months ago

Can I use Llama-2 instead of GPT 3.5 for synthetic data generation?

hadjipantelis commented 7 months ago

@BadrinathMJ Yes, you can. I used it as well as mistral. Just make sure it is used in the generate_queries function.