github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-23 06:01:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #5429] Support converting Starcoder2ForCausalLM from Safetensors #49909

New Issue
Open
opened 2026-04-28 13:23:07 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-28 13:23:07 -05:00
Owner
Copy Link

Originally created by @yaoyasong on GitHub (Jul 2, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5429

What is the issue?

Failed to create starcoder2 model from Modelfile:

Error: Models based on 'Starcoder2ForCausalLM' are not yet supported

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @yaoyasong on GitHub (Jul 2, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5429 ### What is the issue? Failed to create starcoder2 model from Modelfile: Error: Models based on 'Starcoder2ForCausalLM' are not yet supported ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the feature request label 2026-04-28 13:23:07 -05:00
GiteaMirror commented 2026-04-28 13:23:08 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Jul 2, 2024):

Hi @yaoyasong, can you describe the process you are using for importing this model.

Is it from here?
https://huggingface.co/docs/transformers/model_doc/starcoder2#transformers.Starcoder2ForCausalLM

<!-- gh-comment-id:2202614567 --> @igorschlum commented on GitHub (Jul 2, 2024): Hi @yaoyasong, can you describe the process you are using for importing this model. Is it from here? https://huggingface.co/docs/transformers/model_doc/starcoder2#transformers.Starcoder2ForCausalLM
GiteaMirror commented 2026-04-28 13:23:09 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 2, 2024):

What version of ollama are you using? starcoder2 models need ollama version 0.1.28 or better.

<!-- gh-comment-id:2204288366 --> @rick-github commented on GitHub (Jul 2, 2024): What version of ollama are you using? starcoder2 models need ollama version 0.1.28 or better.
GiteaMirror commented 2026-04-28 13:23:09 -05:00
Author
Owner
Copy Link

@geedmo commented on GitHub (Jul 3, 2024):

Similar issue here, trying to import from HF HuggingFaceH4/starchat2-15b-v0.1 (safetensors)
ollama version is 0.1.47

transferring model data
unpacking model metadata
Error: Models based on 'Starcoder2ForCausalLM' are not yet supported
<!-- gh-comment-id:2204895928 --> @geedmo commented on GitHub (Jul 3, 2024): Similar issue here, trying to import from HF HuggingFaceH4/starchat2-15b-v0.1 (safetensors) ollama version is 0.1.47 ``` transferring model data unpacking model metadata Error: Models based on 'Starcoder2ForCausalLM' are not yet supported ```
GiteaMirror commented 2026-04-28 13:23:10 -05:00
Author
Owner
Copy Link

@yaoyasong commented on GitHub (Jul 3, 2024):

Hi @yaoyasong, can you describe the process you are using for importing this model.

Is it from here? https://huggingface.co/docs/transformers/model_doc/starcoder2#transformers.Starcoder2ForCausalLM

I downloaded the model from hf (https://huggingface.co/bigcode/starcoder2-3b) and imported it directly via modelfile
Should I convert the model to gguf format first?

Modelfile:

FROM /path_to_hf_model
TEMPLATE {{ .Prompt }}

ollama version is 0.1.44

<!-- gh-comment-id:2204920007 --> @yaoyasong commented on GitHub (Jul 3, 2024): > Hi @yaoyasong, can you describe the process you are using for importing this model. > > Is it from here? https://huggingface.co/docs/transformers/model_doc/starcoder2#transformers.Starcoder2ForCausalLM I downloaded the model from hf (https://huggingface.co/bigcode/starcoder2-3b) and imported it directly via modelfile Should I convert the model to gguf format first? Modelfile: FROM /path_to_hf_model TEMPLATE {{ .Prompt }} ollama version is 0.1.44
GiteaMirror commented 2026-04-28 13:23:10 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 3, 2024):

Unfortunately Ollama can't (yet) convert directly from the safetensors for starcoder2 (unlike for llama3/gemma), but you should be able to use the convert-hf-to-gguf.py script in thellm/llama.cpp/ directory. Convert the model over to a gguf bin file and then include that in the FROM line of your model file.

<!-- gh-comment-id:2207412565 --> @pdevine commented on GitHub (Jul 3, 2024): Unfortunately Ollama can't (yet) convert directly from the safetensors for starcoder2 (unlike for llama3/gemma), but you should be able to use the `convert-hf-to-gguf.py` script in the`llm/llama.cpp/` directory. Convert the model over to a gguf bin file and then include that in the `FROM` line of your model file.
GiteaMirror commented 2026-04-28 13:23:11 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jul 3, 2024):

If you want to use starcoder2 without having to convert it, just use ollama run starcoder2 of course.

<!-- gh-comment-id:2207413642 --> @pdevine commented on GitHub (Jul 3, 2024): If you want to use starcoder2 without having to convert it, just use `ollama run starcoder2` of course.
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 feature request
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#49909
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?