[GH-ISSUE #3576] Support command r plus #64246

Closed
opened 2026-05-03 16:44:32 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @taozhiyuai on GitHub (Apr 10, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3576

What model would you like?

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

Originally created by @taozhiyuai on GitHub (Apr 10, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3576 ### What model would you like? https://huggingface.co/CohereForAI/c4ai-command-r-plus
GiteaMirror added the model label 2026-05-03 16:44:32 -05:00
Author
Owner

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

It does work fine if you quantize it yourself.

The correct prompt template for using chat is:

TEMPLATE """{{if .System}}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{.System}}<|END_OF_TURN_TOKEN|>{{end}}<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{.Prompt}}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{{.Response}}"""

For RAG and other uses it's slightly different though.

<!-- gh-comment-id:2057718118 --> @jukofyork commented on GitHub (Apr 15, 2024): It does work fine if you quantize it yourself. The correct prompt template for using chat is: ``` TEMPLATE """{{if .System}}<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>{{.System}}<|END_OF_TURN_TOKEN|>{{end}}<|START_OF_TURN_TOKEN|><|USER_TOKEN|>{{.Prompt}}<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>{{.Response}}""" ``` For RAG and other uses it's slightly different though.
Author
Owner

@jmorganca commented on GitHub (Apr 17, 2024):

Hi there, this is fixed in 0.1.32! https://ollama.com/library/command-r-plus

<!-- gh-comment-id:2060142003 --> @jmorganca commented on GitHub (Apr 17, 2024): Hi there, this is fixed in 0.1.32! https://ollama.com/library/command-r-plus
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#64246