github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2462] moondream1 model support #63478

New Issue
Closed
opened 2026-05-03 13:46:58 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-05-03 13:46:58 -05:00
Owner
Copy Link

Originally created by @questsin on GitHub (Feb 12, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2462

how to port the tiny vision model at https://huggingface.co/vikhyatk/moondream1
with Tensor type FP16 using SigLIP, Phi-1.5 and the LLaVa training dataset, to ollama for local ubuntu execution
moondream uses the following python3 libraries

  • accelerate==0.25.0
  • huggingface-hub==0.20.1
  • Pillow==10.1.0
  • torch==2.1.2
  • torchvision==0.16.2
  • transformers==4.36.2
  • einops==0.7.0
  • gradio==4.15.0
  • timm==0.9.12
gh repo clone ollama/ollama
cd ollama
git submodule init
git submodule update llm/llama.cpp

sudo apt install python3.11-venv

python3 -m venv llm/llama.cpp/.venv
source llm/llama.cpp/.venv/bin/activate
pip install -r llm/llama.cpp/requirements.txt

make -C llm/llama.cpp quantize
sudo apt-get install git-lfs
git lfs install
# git clone https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1 model
git clone https://huggingface.co/vikhyatk/moondream1
git lfs pull

# python3 llm/llama.cpp/convert.py ./model --outtype f16 --outfile converted.bin
python3 llm/llama.cpp/convert-hf-to-gguf.py ./model --outtype f16 --outfile converted.bin

# Error output bellow
# Loading model: model
# Traceback (most recent call last):
#   File "/home/questsin/repo/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 1612, in <module>
#     main()
#   File "/home/questsin/repo/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 1593, in main
#     model_instance = model_class(dir_model, ftype_map[args.outtype], fname_out, args.bigendian)
#                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#   File "/home/questsin/repo/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 57, in __init__
#     self.model_arch = self._get_model_architecture()
#                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#   File "/home/questsin/repo/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 262, in _get_model_architecture
#     raise NotImplementedError(f'Architecture "{arch}" not supported!')
# NotImplementedError: Architecture "Moondream" not supported!
Originally created by @questsin on GitHub (Feb 12, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2462 how to port the tiny vision model at https://huggingface.co/vikhyatk/moondream1 with Tensor type FP16 using SigLIP, Phi-1.5 and the LLaVa training dataset, to ollama for local ubuntu execution moondream uses the following python3 libraries - accelerate==0.25.0 - huggingface-hub==0.20.1 - Pillow==10.1.0 - torch==2.1.2 - torchvision==0.16.2 - transformers==4.36.2 - einops==0.7.0 - gradio==4.15.0 - timm==0.9.12 ```bash gh repo clone ollama/ollama cd ollama git submodule init git submodule update llm/llama.cpp sudo apt install python3.11-venv python3 -m venv llm/llama.cpp/.venv source llm/llama.cpp/.venv/bin/activate pip install -r llm/llama.cpp/requirements.txt make -C llm/llama.cpp quantize sudo apt-get install git-lfs git lfs install # git clone https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1 model git clone https://huggingface.co/vikhyatk/moondream1 git lfs pull # python3 llm/llama.cpp/convert.py ./model --outtype f16 --outfile converted.bin python3 llm/llama.cpp/convert-hf-to-gguf.py ./model --outtype f16 --outfile converted.bin # Error output bellow # Loading model: model # Traceback (most recent call last): # File "/home/questsin/repo/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 1612, in <module> # main() # File "/home/questsin/repo/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 1593, in main # model_instance = model_class(dir_model, ftype_map[args.outtype], fname_out, args.bigendian) # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # File "/home/questsin/repo/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 57, in __init__ # self.model_arch = self._get_model_architecture() # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ # File "/home/questsin/repo/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 262, in _get_model_architecture # raise NotImplementedError(f'Architecture "{arch}" not supported!') # NotImplementedError: Architecture "Moondream" not supported! ```
GiteaMirror commented 2026-05-03 13:47:00 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Feb 13, 2024):

Merging with #2259

<!-- gh-comment-id:1942059348 --> @jmorganca commented on GitHub (Feb 13, 2024): Merging with #2259
GiteaMirror commented 2026-05-03 13:47:00 -05:00
Author
Owner
Copy Link

@Kreijstal commented on GitHub (Mar 8, 2024):

could moondream2 be done too?

<!-- gh-comment-id:1986507624 --> @Kreijstal commented on GitHub (Mar 8, 2024): could moondream2 be done too?
GiteaMirror commented 2026-05-03 13:47:01 -05:00
Author
Owner
Copy Link

@Seedmanc commented on GitHub (Jul 5, 2025):

A year passed.

<!-- gh-comment-id:3039069446 --> @Seedmanc commented on GitHub (Jul 5, 2025): A year passed.
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#63478
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?