RAFT and Berkeley Function Calling Leaderboard Updates
😍 v0.2 release 🚀
Highlights
🎯 Berkeley Function Calling Leaderboard (BFCL): How do models stack up for function calling?
- Now includes latency and cost
- More open-source and closed-source models
- Bug fixes in dataset.
RAFT: Fine-tuning technique to improve LLMs for in-domain RAG!
What's Changed
- Adding APIs of 9 Google Service to API Zoo by @meenakshi-mittal in #204
- Github Actions to Maintain API Zoo Index by @ramanv0 in #188
- Adding Zoom API to API Zoo by @meenakshi-mittal in #221
- API Zoo Index Github Actions Fix by @ramanv0 in #261
- Added Google Forms API by @elva01 in #185
- RAFT + readme + small sample dataset by @kaiwen129 in #218
- Sample data for RAFT by @ShishirPatil in #264
- Docusign Additions by @dangeo773 in #194
- [Bug Fix] Fix Executable Exact Match Condition Did not Meet by @Fanjia-Yan in #251
- [Bug Fix] Fix Error in Parallel Function Possible Answer by @Fanjia-Yan in #252
- [Bug Fix] Restrict AST checker on Boolean Variable by @Fanjia-Yan in #256
- Adding 7 Oracle APIs to API Zoo by @meenakshi-mittal in #205
- Adding Datadog API to API Zoo by @meenakshi-mittal in #206
- Added Notion APIs (Block, Page, and Database) to APIZoo by @jennifer818 in #195
- removed testing code by @kaiwen129 in #281
- feat: more type annotations for the functions by @UponTheSky in #283
- [Fix] java, javascript parsers in openfunctions-v2 by @CharlieJCJ in #284
- Leaderboard Update April 1 by @HuanzhiMao in #299
- Remove Large File from
./inference
by @CharlieJCJ in #297 - Typo in raft.py by @danielfleischer in #311
- Leaderboard April 3 release by @HuanzhiMao in #309
- Support OSS Evaluation for Leaderboard by @HuanzhiMao in #318
- Update README.md by @HuanzhiMao in #320
- Fix typos by @viniciuslazzari in #323
- Correction in BFCL README instruction, fixed path in instructions by @CharlieJCJ in #329
New Contributors
- @elva01 made their first contribution in #185
- @kaiwen129 made their first contribution in #218
- @jennifer818 made their first contribution in #195
- @UponTheSky made their first contribution in #283
- @danielfleischer made their first contribution in #311
Full Changelog: v0.1...v0.2