shishirpatil

Hey @behnamoh, maybe you are referring to the community post pre-release? It is still very much live here: https://news.ycombinator.com/item?id=37894403! As we released MemGPT this morning (including discord bot, and on Twitter), we took the community feedback to emphasize more on the context length in the title :) Thank you all for the feedback and keep it coming - we are listening!

Thanks @wilg and @littlestymaar ! Yeah totally, with the benefit of hindsight, this makes total sense! Hope you find some of our codebase useful to build on top of. We are an Apache 2.0 licensed open source project and welcome contributions :)

Yeah! While it’s not known what close-sourced models do, what we think is happening based on some prompt attacks, is that they also use recursive summarization (in addition to what others have mentioned in this thread).

Yeah absolutely! And hopefully with some of the techniques we introduce here, we can think of designing perpetual chat bots!

Check out Gorilla-CLI. An open source alternative to Fig, that’s also LLM powered!

https://github.com/gorilla-llm/gorilla-cli

Thanks for the feedback, @dievskly. Will update it in the next release!

Thanks for sharing @iandanforth and @distortionfield, nice project! Are there any additional features, Gorilla can support to make it useful for you folks!

Thanks for the feedback, @satokema. We currently mention it in our GitHub, pypi readme, and at install. Would you prefer different wording?

I think the use cases are where you roughly remember the commands but not the full command. Like rather than you looking up a man page you could potentially use this. An expert in one field may not be in another, so they might also find this useful!

No commands are executed without the users explicit approval! So, you could always execute any command anyways if you had access to the terminal!

haha. It's a great Open source project!

Thanks @ofermend, we believe that Gorilla will hallucinate lesser than other models but it's not zero yet! We will continue to reduce hallucination. Thanks for the feedback!

Hey @linuxdude314 thank you for the comment. As we mentioned commands are executed solely with your explicit approval; And while we utilize queries and error logs (stderr) for model enhancement, we NEVER collect output data (stdout). This is a stronger guarantee than many of the other LLMs out there and our goal is to help this inform our research.

One of the reasons we open-sourced the front-end, is that if you would like to keep everything private, you can just clone the repo, comment out the logging, install it, and we will still honor and serve your queries if you hit our hosted end-point :) Let us know if there is anything more that we can do to make you comfortable in using our tool!

Oo good suggestion @razzypitaz. We'll try to incorporate this in the next release :) BTW it's open sourced, so if you would be interested in raising a PR would love to have you as a contributor!

Nope. No API key needed since we mostly serve our own Gorilla models.

Yes indeed. The models are too computationally expensive to run locally (7.5Billion parameters). Though you could in-principle swap in any local model.

Hey HN! As one of the contributors and author of Gorilla, we want to express gratitude for your valuable feedback. The community's desire for a straightforward method to invoke Gorilla led to the development of this CLI tool. We appreciate your continued input, so please keep those suggestions coming!

Haha, was busy yesterday! Or was I? :P

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!

Yes, when we released the initial set of models Open Llama was still at 600B checkpoint and not finished training yet. It's an easy port :)

Thanks for the kind words @gsharma! Private APIs is something we are definitely thinking about.

Hi swyx, the weights are also open sourced at https://huggingface.co/gorilla-llm Let us know if you are unable to access them.

Hi @csjh, we trained to model to also additionally output additional context so it would be useful for a downstream task. We wrapped the API call with special decorator so it's easier to just regex. Would you like to just have the API instead? Happy to release an API only model if there is wider interest - It's a strictly easier task for Gorilla LLM :)

Yes we have three set of models. One based on llama - which you are right, cannot be used commercial. We have two additional models based on MPT-7 base and Falcon-7B which can be used commercially with no obligations!

Good point. This was the original release, we now also have Apache-2.0 licensed models finetuned on MPT-7B and Falcon-7B!

Langchain is a terrific project that tries to teach agents how to use tools using prompting. Our take on this is that prompting is not scalable if you want to pick between 1000s of APIs. So Gorilla is a LLM that can pick and write the semantically and syntactically correct API for you to call! A drop in replacement into Langchain!

Hi HN, I'm one of the lead authors on the paper! Gorilla is an open source effort and we would love to hear from the community. Let us know if you have any questions or suggestions!!

A good 32% reduction taking it to less than a 1$ per TB.