David Berenstein: Retrievers and rankers are a crucial part of optimising RAG. Easier to fine-tune than LLMs. More predictable than prompts. Training data is hard to find, so we offer private and free synthetic data on your own documents! Blog:

See full post

David Berenstein davidberenstein.bsky.social
Retrievers and rankers are a crucial part of optimising RAG. Easier to fine-tune than LLMs. More predictable than prompts. Training data is hard to find, so we offer private and free synthetic data on your own documents! Blog:
Fine-tune ModernBERT for RAG with Synthetic Data

A Blog post by Sara Han Díaz on Hugging Face

buff.ly
Feb 4, 2025 16:11
0 reposts 0 quotes 0 likes

View on Bluesky Show all post labels
David Berenstein davidberenstein.bsky.social · Feb 4, 2025
Or use the tool directly! github.com/argilla-io/s...
GitHub - argilla-io/synthetic-data-generator: Build datasets using natural language

Build datasets using natural language. Contribute to argilla-io/synthetic-data-generator development by creating an account on GitHub.

github.com

View on Bluesky Show all post labels

An unhandled error has occurred. Reload 🗙