github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4209] IBM-Granite #64659

New Issue
Closed
opened 2026-05-03 18:27:34 -05:00 by GiteaMirror · 13 comments
GiteaMirror commented 2026-05-03 18:27:34 -05:00
Owner
Copy Link

Originally created by @ALutz273 on GitHub (May 6, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4209

Hello,

Very interesting because of software license

https://github.com/ibm-granite/granite-code-models

Originally created by @ALutz273 on GitHub (May 6, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4209 Hello, Very interesting because of software license https://github.com/ibm-granite/granite-code-models
GiteaMirror added the model label 2026-05-03 18:27:34 -05:00
GiteaMirror commented 2026-05-03 18:27:36 -05:00
Author
Owner
Copy Link

@coder543 commented on GitHub (May 8, 2024):

I'd like to see this as well. Blocked by this issue: https://github.com/ggerganov/llama.cpp/issues/7116

<!-- gh-comment-id:2100973316 --> @coder543 commented on GitHub (May 8, 2024): I'd like to see this as well. Blocked by this issue: https://github.com/ggerganov/llama.cpp/issues/7116
GiteaMirror commented 2026-05-03 18:27:36 -05:00
Author
Owner
Copy Link

@kristofer commented on GitHub (May 12, 2024):

me as well.

<!-- gh-comment-id:2106411012 --> @kristofer commented on GitHub (May 12, 2024): me as well.
GiteaMirror commented 2026-05-03 18:27:37 -05:00
Author
Owner
Copy Link

@coder543 commented on GitHub (May 20, 2024):

Support for the 20B and 34B models seems fine now in llama.cpp, but the latest release of ollama is still missing the necessary commits. I have uploaded a few GGUFs, but trying to load them in ollama just causes a crash. So, hopefully ollama will update their copy of llama.cpp and do a new release soon.

<!-- gh-comment-id:2120628782 --> @coder543 commented on GitHub (May 20, 2024): Support for the 20B and 34B models seems fine now in llama.cpp, but the latest release of ollama is still missing the necessary commits. I [have uploaded](https://github.com/ggerganov/llama.cpp/issues/7116#issuecomment-2120536190) a few GGUFs, but trying to load them in ollama just causes a crash. So, hopefully ollama will update their copy of llama.cpp and do a new release soon.
GiteaMirror commented 2026-05-03 18:27:37 -05:00
Author
Owner
Copy Link

@nurena24 commented on GitHub (May 26, 2024):

Has this been fixed yet?

<!-- gh-comment-id:2132386053 --> @nurena24 commented on GitHub (May 26, 2024): Has this been fixed yet?
GiteaMirror commented 2026-05-03 18:27:39 -05:00
Author
Owner
Copy Link

@coder543 commented on GitHub (May 26, 2024):

The 20B and 34B models are working great on the 0.1.39 pre-release version of ollama: https://ollama.com/library/granite-code

The underlying llama.cpp library still does not support the smaller Granite models, from what I understand.

<!-- gh-comment-id:2132386390 --> @coder543 commented on GitHub (May 26, 2024): The 20B and 34B models are working great on the 0.1.39 pre-release version of ollama: https://ollama.com/library/granite-code The underlying llama.cpp library still does not support the smaller Granite models, from what I understand.
GiteaMirror commented 2026-05-03 18:27:41 -05:00
Author
Owner
Copy Link

@coder543 commented on GitHub (May 28, 2024):

The PR that adds support for small models was just merged into llama.cpp: https://github.com/ggerganov/llama.cpp/pull/7481

Hopefully we can get those models in ollama soon.

<!-- gh-comment-id:2135906877 --> @coder543 commented on GitHub (May 28, 2024): The PR that adds support for small models was just merged into llama.cpp: https://github.com/ggerganov/llama.cpp/pull/7481 Hopefully we can get those models in ollama soon.
GiteaMirror commented 2026-05-03 18:27:42 -05:00
Author
Owner
Copy Link

@DigitLib commented on GitHub (May 29, 2024):

Here is gguf Q5_K_M version that works on llama.cpp. Converted and tested today. Hope to see it soon on ollama.
https://huggingface.co/Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF

Thank you for this great work!

<!-- gh-comment-id:2136891083 --> @DigitLib commented on GitHub (May 29, 2024): Here is gguf Q5_K_M version that works on llama.cpp. Converted and tested today. Hope to see it soon on ollama. https://huggingface.co/Sagicc/granite-8b-code-instruct-Q5_K_M-GGUF Thank you for this great work!
GiteaMirror commented 2026-05-03 18:27:43 -05:00
Author
Owner
Copy Link

@sroecker commented on GitHub (Jun 3, 2024):

I think this can be closed now. @jmorganca

<!-- gh-comment-id:2144746249 --> @sroecker commented on GitHub (Jun 3, 2024): I think this can be closed now. @jmorganca
GiteaMirror commented 2026-05-03 18:27:44 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jun 4, 2024):

https://ollama.com/library/granite-code @sroecker thanks!

<!-- gh-comment-id:2146743176 --> @jmorganca commented on GitHub (Jun 4, 2024): https://ollama.com/library/granite-code @sroecker thanks!
GiteaMirror commented 2026-05-03 18:27:44 -05:00
Author
Owner
Copy Link

@ericcurtin commented on GitHub (Jul 26, 2024):

I think we messed up the naming here to be honest, I tried a

ollama pull granite

nothing happened. I'm not sure how many would instinctively include the "-code".

What do you think @sroecker ?

Could we claim/migrate to https://ollama.com/library/granite ? @jmorganca would it be possible?

I've never heard anyone call it "Granite code" and I've heard about IBM's granite model a lot.

<!-- gh-comment-id:2252504848 --> @ericcurtin commented on GitHub (Jul 26, 2024): I think we messed up the naming here to be honest, I tried a ollama pull granite nothing happened. I'm not sure how many would instinctively include the "-code". What do you think @sroecker ? Could we claim/migrate to https://ollama.com/library/granite ? @jmorganca would it be possible? I've never heard anyone call it "Granite code" and I've heard about IBM's granite model a lot.
GiteaMirror commented 2026-05-03 18:27:44 -05:00
Author
Owner
Copy Link

@coder543 commented on GitHub (Jul 26, 2024):

@ericcurtin I’m not a maintainer here, but I’ll point out that IBM Granite is largely unrelated to the IBM Granite Code models, and I’ve had the opposite anecdotal experience.

<!-- gh-comment-id:2252620860 --> @coder543 commented on GitHub (Jul 26, 2024): @ericcurtin I’m not a maintainer here, but I’ll point out that [IBM Granite](https://huggingface.co/ibm-granite/granite-7b-base) is largely unrelated to the IBM Granite Code models, and I’ve had the opposite anecdotal experience.
GiteaMirror commented 2026-05-03 18:27:45 -05:00
Author
Owner
Copy Link

@ericcurtin commented on GitHub (Jul 26, 2024):

@coder543 yes you are correct, I think I have to train myself up on IBM Granite. code is the IBM Granite model specifically designed for code.

<!-- gh-comment-id:2252631799 --> @ericcurtin commented on GitHub (Jul 26, 2024): @coder543 yes you are correct, I think I have to train myself up on IBM Granite. code is the IBM Granite model specifically designed for code.
GiteaMirror commented 2026-05-03 18:27:45 -05:00
Author
Owner
Copy Link

@sroecker commented on GitHub (Jul 26, 2024):

@ericcurtin I’m not a maintainer here, but I’ll point out that IBM Granite is largely unrelated to the IBM Granite Code models, and I’ve had the opposite anecdotal experience.

Indeed, I think it's good to keep them separate. The code models themselves are already a bit confusing due to their different archictectures. Also, imagine a few additional non-code models coming out making it even more confusing.

<!-- gh-comment-id:2252649896 --> @sroecker commented on GitHub (Jul 26, 2024): > @ericcurtin I’m not a maintainer here, but I’ll point out that [IBM Granite](https://huggingface.co/ibm-granite/granite-7b-base) is largely unrelated to the IBM Granite Code models, and I’ve had the opposite anecdotal experience. Indeed, I think it's good to keep them separate. The code models themselves are already a bit confusing due to their different archictectures. Also, imagine a few additional non-code models coming out making it even more confusing.
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#64659
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?