github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #468] Add Refact model #218

New Issue
Closed
opened 2026-04-12 09:44:22 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-12 09:44:22 -05:00
Owner
Copy Link

Originally created by @Alainx277 on GitHub (Sep 5, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/468

A new 1.6b parameter model called "Refact" has been released.

Blog post

Hugging Face

I tried adding it myself, but the llama.cpp scripts to convert to GGML format did not work. Keep in mind that I'm a novice in this area, and it may work with the correct arguments.

Originally created by @Alainx277 on GitHub (Sep 5, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/468 A new 1.6b parameter model called "Refact" has been released. [Blog post](https://refact.ai/blog/2023/introducing-refact-code-llm/) [Hugging Face](https://huggingface.co/smallcloudai/Refact-1_6B-fim) I tried adding it myself, but the llama.cpp scripts to convert to GGML format did not work. Keep in mind that I'm a novice in this area, and it may work with the correct arguments.
GiteaMirror added the model label 2026-04-12 09:44:22 -05:00
GiteaMirror commented 2026-04-12 09:44:23 -05:00
Author
Owner
Copy Link

@technovangelist commented on GitHub (Dec 4, 2023):

It looks like that model is using an architecture called GPTRefactForCausalLM which is not one supported by Ollama.

<!-- gh-comment-id:1839311446 --> @technovangelist commented on GitHub (Dec 4, 2023): It looks like that model is using an architecture called GPTRefactForCausalLM which is not one supported by Ollama.
GiteaMirror commented 2026-04-12 09:44:24 -05:00
Author
Owner
Copy Link

@coder543 commented on GitHub (Jan 25, 2024):

llama.cpp claims to support Refact. Possibly added in this PR, and discussed here.. So, I would expect this to be relatively straightforward now, but I haven't tested it myself yet, just making a note here.

<!-- gh-comment-id:1911187197 --> @coder543 commented on GitHub (Jan 25, 2024): llama.cpp claims to support Refact. Possibly [added in this PR](https://github.com/ggerganov/llama.cpp/pull/3329), and [discussed here.](https://github.com/ggerganov/llama.cpp/issues/3061). So, I would expect this to be relatively straightforward now, but I haven't tested it myself yet, just making a note here.
GiteaMirror commented 2026-04-12 09:44:24 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Dec 23, 2024):

This should be possible by importing existing models with this architecture (in GGUF for now). Thanks for the issue!

<!-- gh-comment-id:2558699725 --> @jmorganca commented on GitHub (Dec 23, 2024): This should be possible by importing existing models with this architecture (in GGUF for now). Thanks for the issue!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label model
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#218
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?