github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-05 23:53:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #11968] 🛑 starcoder:latest model cannot be used in Ollama — lacks generate support #7947

New Issue
Closed
opened 2026-04-12 20:06:41 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 20:06:41 -05:00
Owner
Copy Link

Originally created by @Trishvan on GitHub (Aug 19, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11968

Hi team,

I noticed that the starcoder:latest model is listed on [ollama.com/library/starcoder](https://ollama.com/library/starcoder) and available for pull via:

ollama pull starcoder

However, after pulling the model, it’s completely unusable:

  • ollama run starcoder →
    ❌ Error: "starcoder" does not support generate
  • Trying to wrap it with a Modelfile →
    ❌ Same error
  • Using /api/chat →
    ❌ "error": "\"starcoder\" does not support chat"
  • Trying /api/completions →
    ❌ 404 Not Found

This suggests the model does not implement any of the public interfaces Ollama supports (generate, chat, or completions). So effectively, it’s unusable for end users.

🙏 Request:

Please either:

  1. Clearly mark this model as unsupported or experimental on the website.
  2. Or hide it from the public registry until it supports basic functionality (generate at minimum).
  3. Or document how it is meant to be used (if it’s for internal use or fine-tuning only).

This would help avoid a lot of user confusion and frustration.

Thanks!

Originally created by @Trishvan on GitHub (Aug 19, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11968 Hi team, I noticed that the `starcoder:latest` model is listed on [[ollama.com/library/starcoder](https://ollama.com/library/starcoder)](https://ollama.com/library/starcoder) and available for pull via: ```bash ollama pull starcoder ``` However, after pulling the model, it’s completely unusable: * `ollama run starcoder` → ❌ `Error: "starcoder" does not support generate` * Trying to wrap it with a `Modelfile` → ❌ Same error * Using `/api/chat` → ❌ `"error": "\"starcoder\" does not support chat"` * Trying `/api/completions` → ❌ 404 Not Found This suggests the model does **not** implement any of the public interfaces Ollama supports (`generate`, `chat`, or `completions`). So effectively, it’s **unusable** for end users. --- ### 🙏 Request: Please either: 1. Clearly mark this model as **unsupported or experimental** on the website. 2. Or hide it from the public registry until it supports basic functionality (`generate` at minimum). 3. Or document how it *is* meant to be used (if it’s for internal use or fine-tuning only). --- This would help avoid a lot of user confusion and frustration. Thanks!
GiteaMirror commented 2026-04-12 20:06:43 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 19, 2025):

$ ollama pull starcoder 
pulling manifest 
pulling b4a4eea1f5d8: 100% ▕███████████████████████████████████████████████████████████████▏ 1.8 GB                         
pulling 1576480a555b: 100% ▕███████████████████████████████████████████████████████████████▏   36 B                         
pulling f5664457ab5c: 100% ▕███████████████████████████████████████████████████████████████▏  311 B                         
verifying sha256 digest 
writing manifest 
success 

$ ollama run starcoder 'def hello_world():'

    return 'Hello world!'

if __name__ == '__main__':
   app.run()


$ ollama -v
ollama version is 0.11.5-rc2
$ ollama list starcoder
NAME                   ID              SIZE      MODIFIED      
starcoder:latest       847e5a7aa26f    1.8 GB    3 minutes ago
<!-- gh-comment-id:3202043049 --> @rick-github commented on GitHub (Aug 19, 2025): ```console $ ollama pull starcoder pulling manifest pulling b4a4eea1f5d8: 100% ▕███████████████████████████████████████████████████████████████▏ 1.8 GB pulling 1576480a555b: 100% ▕███████████████████████████████████████████████████████████████▏ 36 B pulling f5664457ab5c: 100% ▕███████████████████████████████████████████████████████████████▏ 311 B verifying sha256 digest writing manifest success ``` ```console $ ollama run starcoder 'def hello_world():' return 'Hello world!' if __name__ == '__main__': app.run() ``` ```console $ ollama -v ollama version is 0.11.5-rc2 $ ollama list starcoder NAME ID SIZE MODIFIED starcoder:latest 847e5a7aa26f 1.8 GB 3 minutes ago ```
GiteaMirror commented 2026-04-12 20:06:44 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Aug 19, 2025):

@Trishvan the AI you used to generate the issue is hallucinating. Starcoder is a text model and not an instruct model though so you'll have a hard time chatting with it, but both /api/generate and /api/chat work correctly. See @rick-github 's examples above, or try the API directly.

<!-- gh-comment-id:3202657481 --> @pdevine commented on GitHub (Aug 19, 2025): @Trishvan the AI you used to generate the issue is hallucinating. Starcoder is a text model and not an instruct model though so you'll have a hard time chatting with it, but both `/api/generate` and `/api/chat` work correctly. See @rick-github 's examples above, or try the API directly.
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#7947
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?