gorilla

Retrieval-Augmented Fine-Tuning is a really promising technique. FTA: > Tianjun and Shishir were looking to improve these deficiencies of RAG. They hypothesized that a student who studies the textbooks before the open-book exam would be more likely to perform better than a student who references the textbook only during the exam. Translating that back to LLMs, if a model “studied” the documents beforehand, could that improve its RAG performance? Incidentally, the team who wrote the paper released some nice code to generate domain-specific fine-tuning datasets: https://github.com/ShishirPatil/gorilla/tree/main/raft

Author of Gorilla Execution Engine (GoEx) here! The key idea behind GoEx: 1. "Post-facto validation" for assessing LLM actions after execution. 2. "Undo" button and “Damage confinement” abstractions to manage unintended actions & risks! GoEx (code below) inherently supports Gmail/Slack/Dropbox/Spotify/Github, try it out to build your own LLM agents! Blog: https://gorilla.cs.berkeley.edu/blogs/10_gorilla_exec_engine... Code: https://github.com/ShishirPatil/gorilla/tree/main/goex

There are now several open source models that are fine tuned for function calling including: * Functionary [https://github.com/MeetKai/functionary] * NexusRaven [https://github.com/nexusflowai/NexusRaven-V2] * Gorilla [https://github.com/ShishirPatil/gorilla] Could be interesting to try some of these exercises with these models.

Nice this made me go back and check up on the Gorilla LLM project [1] to see whats they are doing with API and if they have applied their fine tuning to any of the newer foundation models but looks like things have slowed down since they launched (?) or maybe development is happening elsewhere on some invisible discord channel but I hope the intersection of API calling and LLM as a logic processing function keep getting focus it's an important direction for interop across the web. [1] https://github.com/ShishirPatil/gorilla

"Gorilla: Large Language Model Connected with Massive APIs" (2023) https://gorilla.cs.berkeley.edu/ : > Gorilla enables LLMs to use tools by invoking APIs. Given a natural language query, Gorilla comes up with the semantically- and syntactically- correct API to invoke. With Gorilla, we are the first to demonstrate how to use LLMs to invoke 1,600+ (and growing) API calls accurately while reducing hallucination. We also release APIBench, the largest collection of APIs, curated and easy to be trained on! Join us, as we try to expand the largest API store and teach LLMs how to write them! eval/: https://github.com/ShishirPatil/gorilla/tree/main/eval - "Gorilla: Large Language Model connected with massive APIs" (2023-05) https://news.ycombinator.com/item?id=36073241 - "Gorilla: Large Language Model Connected with APIs" (2023-06) https://news.

This looks neat. https://github.com/ShishirPatil/gorilla feels like a project with certain similarities here. How would you compare yourselves to them?

Thanks @sfriedr We generate self-instruct data and then fine tune the base model with perplexity loss. The self-instruct data is https://github.com/ShishirPatil/gorilla/tree/main/data/apibe... Thank you! Yes, the code can be found here: https://github.com/ShishirPatil/gorilla/tree/main/eval/eval-... Hope this helps. Let me know if you have any follow-ups!