[GH-ISSUE #546] [FEAT] Add token length control to the Native LLM provider #321

Closed
opened 2026-02-22 18:18:56 -05:00 by yindo · 0 comments
Owner

Originally created by @timothycarambat on GitHub (Jan 5, 2024).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/546

Originally assigned to: @shatfield4 on GitHub.

RIght now, we allow users to put GGUF models into a downloaded folder that can then be used with LlamaCPP but the issue is we cannot control the max token limit and it is fixed at 4096.

This limit is not ubiquitous for all LLM models and you should be able to modify it.

Originally created by @timothycarambat on GitHub (Jan 5, 2024). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/546 Originally assigned to: @shatfield4 on GitHub. RIght now, we allow users to put GGUF models into a `downloaded` folder that can then be used with `LlamaCPP` but the issue is we cannot control the max token limit and it is fixed at `4096`. This limit is not ubiquitous for all LLM models and you should be able to modify it.
yindo added the enhancementIntegration Requestfeature request labels 2026-02-22 18:18:56 -05:00
yindo closed this issue 2026-02-22 18:18:56 -05:00
yindo changed title from [FEAT] Add token length control to the `Native` LLM provider to [GH-ISSUE #546] [FEAT] Add token length control to the `Native` LLM provider 2026-06-05 14:34:41 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#321