ROCm / ROCm/FastFlowLM

Adding own models

Open
#246 21 comments 18 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
1.9k
Forks
152
Avg merge
4h 14m
Merged PRs (30d)
11

Description

Hi there,

Could you add a section to your documentation about the steps required for the user to add their own models? I'd like to be able to add every GGUF model I want, converting it first of course. But I cannot seem to find a reasonably good tutorial on the matter that doesn't require me to be an LLM expert to follow it in the first place.

Maybe there could even be a commandline option in FFLM itself like -add-gguf model-path that automatically converts the model and, after asking the user for the information needed (name etc) adds it to FFLM automatically.

Thanks a lot in advance and thanks for this amazing piece of software!

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no files, tests, or entry points. Start by locating the existing documentation and the model conversion and registration workflow, then document the steps and required model information for adding a converted GGUF model; treat the proposed automatic command-line option as a separate scope decision.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
documentation
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
52/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.