Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #631] [FEAT]: Parameter-efficient fine-tuning LLM based on uploaded user documents #358

New Issue
Closed
opened 2026-02-22 18:19:07 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:19:07 -05:00
Owner
Copy Link
Copy Source

Originally created by @Mirgiacomo on GitHub (Jan 20, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/631

Do you think it might be useful to implement a section where the user can fine tune a file?

By fine-tuning I mean either full fine-tuning or Parameter-efficient fine-tuning.
Where the user based on the documents they have uploaded can train a model with their knowledge.
Is it too onerous (both from the point of view of implementation time and resources needed) or can it be done / do you already have plans to do it?

Originally created by @Mirgiacomo on GitHub (Jan 20, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/631 Do you think it might be useful to implement a section where the user can fine tune a file? By fine-tuning I mean either full fine-tuning or Parameter-efficient fine-tuning. Where the user based on the documents they have uploaded can train a model with their knowledge. Is it too onerous (both from the point of view of implementation time and resources needed) or can it be done / do you already have plans to do it?
yindo added the enhancementfeature request labels 2026-02-22 18:19:07 -05:00
yindo closed this issue 2026-02-22 18:19:07 -05:00
yindo commented 2026-02-22 18:19:07 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jan 22, 2024):

While this would be great to support, building out the training pipeline inside of AnythingLLM would be a whole other undertaking in and of itself! Training is really only realistic on GPUs and even then there is a lot of nuance in how to do the training and if the model can even be trained (open-souce only obviously).

However, our effort to support this in the scope of AnythingLLM is allowing exports of all chats from the instance, which can be used for training. Obviously, you would need to comb through the results to get what you ideally want to include, but that is as far as we can take it and then the user would need to go an do the training however they want to, but at least have the data now!

@timothycarambat commented on GitHub (Jan 22, 2024): While this would be great to support, building out the training pipeline inside of AnythingLLM would be a whole other undertaking in and of itself! Training is really only realistic on GPUs and even then there is a lot of nuance in _how_ to do the training and if the model can even be trained (open-souce only obviously). However, our effort to support this in the scope of AnythingLLM is allowing exports of all chats from the instance, which _can_ be used for training. Obviously, you would need to comb through the results to get what you ideally want to include, but that is as far as we can take it and then the user would need to go an do the training however they want to, but at least have the data now!
yindo changed title from [FEAT]: Parameter-efficient fine-tuning LLM based on uploaded user documents to [GH-ISSUE #631] [FEAT]: Parameter-efficient fine-tuning LLM based on uploaded user documents 2026-06-05 14:34:54 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label enhancement feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#358
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?