gptqlora VS gorilla

GPTQLoRA: Efficient Finetuning of Quantized LLMs with GPTQ (https://github.com/qwopqwop200/gptqlora/tree/main)

The difference from QLoRA is that GPTQ is used instead of NF4 (Normal Float4) + DQ (Double Quantization) for model quantization. The advantage is that you can expect better performance because it provides better quantization than conventional bitsandbytes. The downside is that it is a one-shot quantization methodology, so it is more inconvenient than bitsandbytes, and unlike bitsandbytes, it is not universal. I'm still experimenting, but it seems to work. At least, I hope it can be more options for people using LoRA. https://github.com/qwopqwop200/gptqlora/tree/main

Do you leverage https://gorilla.cs.berkeley.edu/ at all? If not, perhaps consider if it would solve some pain for you.

* Gorilla [https://github.com/ShishirPatil/gorilla]

Could be interesting to try some of these exercises with these models.

gorilla

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/:

Humans of AI Podcast #7

An amazing conversation with Shishir Patil the creator of the Gorilla LLM, a large language model specifically trained to use APIs!

Shishir is currently a 5th year PhD student at the University of California, Berkeley whose work broadly covers ML-Systems, LLMs, Edge-ML, and Sky computing.

Definitely give the episode a listen to hear Shishir's story.

And to read more about #GorillaLLM, check out the project page!

https://gorilla.cs.berkeley.edu