github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #3100] C4AI Command #63942

New Issue
Closed
opened 2026-05-03 15:31:43 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-03 15:31:43 -05:00
Owner
Copy Link

Originally created by @AdaptiveStep on GitHub (Mar 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3100

Please add the c4ai-command model
Its really good at translation and can handle 100 languages.

https://huggingface.co/CohereForAI/c4ai-command-r-v01

Originally created by @AdaptiveStep on GitHub (Mar 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3100 Please add the c4ai-command model Its really good at translation and can handle 100 languages. https://huggingface.co/CohereForAI/c4ai-command-r-v01
GiteaMirror added the model label 2026-05-03 15:31:43 -05:00
GiteaMirror commented 2026-05-03 15:32:06 -05:00
Author
Owner
Copy Link

@salah55s commented on GitHub (Mar 13, 2024):

Also supporting the quantized versions.. as it's normal is 50+ GB

<!-- gh-comment-id:1994273239 --> @salah55s commented on GitHub (Mar 13, 2024): Also supporting the quantized versions.. as it's normal is 50+ GB
GiteaMirror commented 2026-05-03 15:32:07 -05:00
Author
Owner
Copy Link

@simsi-andy commented on GitHub (Mar 16, 2024):

The model has already been created and it has been implemented (merged) into llama.cpp. How can it be used here?

https://huggingface.co/andrewcanis/c4ai-command-r-v01-GGUF

https://github.com/ggerganov/llama.cpp/pull/6033

<!-- gh-comment-id:2001992779 --> @simsi-andy commented on GitHub (Mar 16, 2024): The model has already been created and it has been implemented (merged) into llama.cpp. How can it be used here? https://huggingface.co/andrewcanis/c4ai-command-r-v01-GGUF https://github.com/ggerganov/llama.cpp/pull/6033
GiteaMirror commented 2026-05-03 15:32:08 -05:00
Author
Owner
Copy Link

@Noeda commented on GitHub (Mar 16, 2024):

Hey folks. I believe there is a slight issue with tokenization on Command-R on llama.cpp (just opened https://github.com/ggerganov/llama.cpp/issues/6104). I don't think it impacts output quality in a material way but if we've got invested people here on Command-R model maybe you'll just want that issue on your notifications. I plan to investigate it in more detail some time next week.

The tokenization divergence between llama.cpp and Command-R Huggingface implementation sometimes seems to slightly re-order top logits depending on how much the tokenization diverges based on your prompt, which can impact what it outputs. But I haven't empirically seen any degradation of quality.

<!-- gh-comment-id:2002037424 --> @Noeda commented on GitHub (Mar 16, 2024): Hey folks. I believe there is a slight issue with tokenization on Command-R on llama.cpp (just opened https://github.com/ggerganov/llama.cpp/issues/6104). I don't think it impacts output quality in a material way but if we've got invested people here on Command-R model maybe you'll just want that issue on your notifications. I plan to investigate it in more detail some time next week. The tokenization divergence between `llama.cpp` and Command-R Huggingface implementation sometimes seems to slightly re-order top logits depending on how much the tokenization diverges based on your prompt, which can impact what it outputs. But I haven't empirically seen any degradation of quality.
GiteaMirror commented 2026-05-03 15:32:09 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Apr 15, 2024):

Hi! Really sorry for the slow reply to this issue. We've added Command-R model from Cohere to the model library.

https://ollama.com/library/command-r

We're working on Command R Plus model right now, and is available in the pre-release build of Ollama.

Please let us know if you run into any problems! Again, sorry for the slow reply.

<!-- gh-comment-id:2057154891 --> @mchiang0610 commented on GitHub (Apr 15, 2024): Hi! Really sorry for the slow reply to this issue. We've added Command-R model from Cohere to the model library. https://ollama.com/library/command-r We're working on Command R Plus model right now, and is available in the pre-release build of Ollama. Please let us know if you run into any problems! Again, sorry for the slow reply.
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#63942
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?