Re:Gorilla: Large Language Model Connected with APIs
by data_maan on Friday June 16, 2023 @04:02AM
(#36353062)
Seems @shishirpatil ran out of steam answering questions. Too bad.
Re:Gorilla: Large Language Model Connected with APIs
by data_maan on Friday June 16, 2023 @05:06PM
(#36363880)
(Or maybe the questions were too tricky and he wasn't able to answer, heh)
Re:Gorilla: Large Language Model Connected with APIs
by shishirpatil on Friday June 16, 2023 @11:59PM
(#36367137)
Haha, was busy yesterday! Or was I? :P
Re:Gorilla: Large Language Model Connected with APIs
by shishirpatil on Friday June 16, 2023 @11:58PM
(#36367134)
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!
Re:Gorilla: Large Language Model Connected with APIs
by data_maan on Saturday June 17, 2023 @06:12AM
(#36368845)
Awesome, thanks for letting me know!
I'm still not sure though about some nitpicky things: - do you change all the weights, or just the ones from the last layer when fine-tuning? - do you just train on the _code_ field from the JSON file with the self-instruct data, or do you also use the other fields to train (or do you use the other fields just for downstream evaluation purposes)?
I think it could be a major selling point of your paper if on Github (or in an appendix to your preprint, if you update it on arxiv), you had a section where you document the training process in detail
I have a few questions:
* you say (page 4): "We then perform standard instruction finetuning on the base LLaMA-7B model" Could you perhaps provide a reference to the _exact_ finetuning approach you used? I'm afraid different groups of people have a different notion of "standart" (see for example pages 131-155 from https://arxiv.org/abs/2302.08575 for various fine-tuning approaches) and without knowing exactly how fine-tuning was carried out, it can be very difficult reproduce your research and results exactly.
* the idea of using AST Sub-Tree Matching is nice. Could you please let me know which function in which file from your GitHub repository this is implemented in?
Again, great job on publishing this paper!
---
Best regards,
friederrr.org