github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3532] CohereForAI / c4ai-command-r-plus-4bit #48688

New Issue
Closed
opened 2026-04-28 09:05:59 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-28 09:05:59 -05:00
Owner
Copy Link

Originally created by @petunder on GitHub (Apr 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3532

What model would you like?

C4AI Command R+ is an open weights research release of a 104B billion parameter model with highly advanced capabilities, this includes Retrieval Augmented Generation (RAG) and tool use to automate sophisticated tasks.

https://huggingface.co/CohereForAI/c4ai-command-r-plus-4bit

This model is split into individual files, which makes direct uploading difficult. Additionally, the model is in the .safetensors format.

Originally created by @petunder on GitHub (Apr 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3532 ### What model would you like? C4AI Command R+ is an open weights research release of a 104B billion parameter model with highly advanced capabilities, this includes Retrieval Augmented Generation (RAG) and tool use to automate sophisticated tasks. https://huggingface.co/CohereForAI/c4ai-command-r-plus-4bit This model is split into individual files, which makes direct uploading difficult. Additionally, the model is in the .safetensors format.
GiteaMirror commented 2026-04-28 09:06:01 -05:00
Author
Owner
Copy Link

@petunder commented on GitHub (Apr 8, 2024):

Command R Plus currently requires rebuilding Ollama with the llama.cpp branch from this PR: https://github.com/ggerganov/llama.cpp/pull/6491

<!-- gh-comment-id:2042444825 --> @petunder commented on GitHub (Apr 8, 2024): Command R Plus currently requires rebuilding Ollama with the llama.cpp branch from this PR: https://github.com/ggerganov/llama.cpp/pull/6491
GiteaMirror commented 2026-04-28 09:06:01 -05:00
Author
Owner
Copy Link

@jason-c-kwan commented on GitHub (Apr 8, 2024):

@petunder Do instructions exist somewhere on how to build ollama with a different commit/PR of llama.cpp? I have not been able to get it to work so far.

<!-- gh-comment-id:2043606924 --> @jason-c-kwan commented on GitHub (Apr 8, 2024): @petunder Do instructions exist somewhere on how to build ollama with a different commit/PR of llama.cpp? I have not been able to get it to work so far.
GiteaMirror commented 2026-04-28 09:06:02 -05:00
Author
Owner
Copy Link

@petunder commented on GitHub (Apr 9, 2024):

@petunder Do instructions exist somewhere on how to build ollama with a different commit/PR of llama.cpp? I have not been able to get it to work so far.

Two hours ago @ggerganov updated llama.cpp code, so you can build ollama from source as usual, all things should work

<!-- gh-comment-id:2044681531 --> @petunder commented on GitHub (Apr 9, 2024): > @petunder Do instructions exist somewhere on how to build ollama with a different commit/PR of llama.cpp? I have not been able to get it to work so far. Two hours ago @ggerganov updated llama.cpp code, so you can build ollama from source as usual, all things should work
GiteaMirror commented 2026-04-28 09:06:03 -05:00
Author
Owner
Copy Link

@taozhiyuai commented on GitHub (Apr 9, 2024):

support! I need command r plus on ollama. :_)

<!-- gh-comment-id:2045212455 --> @taozhiyuai commented on GitHub (Apr 9, 2024): support! I need command r plus on ollama. :_)
GiteaMirror commented 2026-04-28 09:06:04 -05:00
Author
Owner
Copy Link

@jason-c-kwan commented on GitHub (Apr 9, 2024):

@petunder Building does not work for me. Doing go build . gives me this error:

# github.com/ollama/ollama/llm
llm/server.go:68:28: undefined: gpu.CheckVRAM
llm/server.go:69:14: undefined: gpu.GetGPUInfo

...and the executables are not made. Am I missing something obvious here or should I submit a separate issue?

<!-- gh-comment-id:2045370811 --> @jason-c-kwan commented on GitHub (Apr 9, 2024): @petunder Building does not work for me. Doing `go build .` gives me this error: ``` # github.com/ollama/ollama/llm llm/server.go:68:28: undefined: gpu.CheckVRAM llm/server.go:69:14: undefined: gpu.GetGPUInfo ``` ...and the executables are not made. Am I missing something obvious here or should I submit a separate issue?
GiteaMirror commented 2026-04-28 09:06:04 -05:00
Author
Owner
Copy Link

@jason-c-kwan commented on GitHub (Apr 9, 2024):

Oh, I figured it out. For anyone else who comes across the same issue - the problem was I was building in a conda environment. Installing go 1.22 on the base system made it work.

<!-- gh-comment-id:2045593108 --> @jason-c-kwan commented on GitHub (Apr 9, 2024): Oh, I figured it out. For anyone else who comes across the same issue - the problem was I was building in a conda environment. Installing go 1.22 on the base system made it work.
GiteaMirror commented 2026-04-28 09:06:05 -05:00
Author
Owner
Copy Link

@trinque commented on GitHub (Apr 9, 2024):

https://github.com/ggerganov/llama.cpp/pull/6491 has been merged.

<!-- gh-comment-id:2046072286 --> @trinque commented on GitHub (Apr 9, 2024): https://github.com/ggerganov/llama.cpp/pull/6491 has been merged.
GiteaMirror commented 2026-04-28 09:06:05 -05:00
Author
Owner
Copy Link

@jason-c-kwan commented on GitHub (Apr 9, 2024):

Just opened a new issue (#3563 ) because I figured this one is specifically for requesting the 4-bit version. I have not been able to import either version of the GGUFs I could find on Hugging Face and not all the quants are yet available on ollama hub.

<!-- gh-comment-id:2046109339 --> @jason-c-kwan commented on GitHub (Apr 9, 2024): Just opened a new issue (#3563 ) because I figured this one is specifically for requesting the 4-bit version. I have not been able to import either version of the GGUFs I could find on Hugging Face and not all the quants are yet available on ollama hub.
GiteaMirror commented 2026-04-28 09:06:06 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Apr 12, 2024):

Let's cover this in #3576 . The changes are already merged and should be available in 0.1.32.

<!-- gh-comment-id:2052386825 --> @pdevine commented on GitHub (Apr 12, 2024): Let's cover this in #3576 . The changes are already merged and should be available in `0.1.32`.
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
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#48688
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?