github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1097] How to create model from Modelfile when the model is splitted into multiple .bin files? #546

New Issue
Closed
opened 2026-04-12 10:14:02 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 10:14:02 -05:00
Owner
Copy Link

Originally created by @kasperjunge on GitHub (Nov 12, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1097

I have a pretty basic question. I want to run this model with Ollama.

I download it from Hugging Face Hub using this script:

from huggingface_hub import snapshot_download

model_id = "mhenrichsen/hestenettetLM"
snapshot_download(
    repo_id=model_id,
    local_dir="hestenettetLM",
    local_dir_use_symlinks=False,
    revision="main",
)

Then I get a dir that looks like this:

.
├── README.md
├── added_tokens.json
├── config.json
├── generation_config.json
├── pytorch_model-00001-of-00002.bin
├── pytorch_model-00002-of-00002.bin
├── pytorch_model.bin.index.json
├── special_tokens_map.json
├── tokenizer.model
└── tokenizer_config.json

I now want to make a Modelfile so I can run it with Ollama.

This guide instructs me to create a Modelfile with the following content:

FROM ./q4_0.bin

And the run:

ollama create example -f Modelfile

However, my model is splitted into two .bin files. I put my Modelfile in the downloaded model dir and I have tried:

# Modelfile
FROM ./pytorch_model-00001-of-00002.bin ./pytorch_model-00002-of-00002.bin

# Terminal output
pulling manifest  Error: pull model manifest: Get "https://./v2/pytorch_model-00001-of-00002.bin%!/(MISSING)pytorch_model-00002-of-00002.bin/manifests/latest": dial tcp: lookup .: no such host

# Modelfile
FROM ./pytorch_model-00001-of-00002.bin
FROM ./pytorch_model-00002-of-00002.bin

# Terminal output
parsing modelfile    
looking for model    
⠋ creating model layer  Error: invalid file magic

# Modelfile
FROM ./pytorch_model-00001-of-00002.bin

# Terminal output
parsing modelfile    
looking for model    
⠋ creating model layer  Error: invalid file magic

# Modelfile
FROM .

# Terminal output
parsing modelfile    
looking for model    
⠋ creating model layer  Error: invalid file magic

My question:

How can I create a model from Modelfile when the model is splitted into multiple .bin files?

Originally created by @kasperjunge on GitHub (Nov 12, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1097 I have a pretty basic question. I want to run [this model](https://huggingface.co/mhenrichsen/hestenettetLM) with Ollama. I download it from Hugging Face Hub using this script: ````python from huggingface_hub import snapshot_download model_id = "mhenrichsen/hestenettetLM" snapshot_download( repo_id=model_id, local_dir="hestenettetLM", local_dir_use_symlinks=False, revision="main", ) ```` Then I get a dir that looks like this: ```` . ├── README.md ├── added_tokens.json ├── config.json ├── generation_config.json ├── pytorch_model-00001-of-00002.bin ├── pytorch_model-00002-of-00002.bin ├── pytorch_model.bin.index.json ├── special_tokens_map.json ├── tokenizer.model └── tokenizer_config.json ```` I now want to make a Modelfile so I can run it with Ollama. [This guide](https://github.com/jmorganca/ollama/blob/main/docs/import.md) instructs me to create a Modelfile with the following content: ```` FROM ./q4_0.bin ```` And the run: ````bash ollama create example -f Modelfile ```` However, my model is splitted into two .bin files. I put my Modelfile in the downloaded model dir and I have tried: 1. ```` # Modelfile FROM ./pytorch_model-00001-of-00002.bin ./pytorch_model-00002-of-00002.bin # Terminal output pulling manifest Error: pull model manifest: Get "https://./v2/pytorch_model-00001-of-00002.bin%!/(MISSING)pytorch_model-00002-of-00002.bin/manifests/latest": dial tcp: lookup .: no such host ```` 2. ```` # Modelfile FROM ./pytorch_model-00001-of-00002.bin FROM ./pytorch_model-00002-of-00002.bin # Terminal output parsing modelfile looking for model ⠋ creating model layer Error: invalid file magic ```` 3. ```` # Modelfile FROM ./pytorch_model-00001-of-00002.bin # Terminal output parsing modelfile looking for model ⠋ creating model layer Error: invalid file magic ```` 4. ```` # Modelfile FROM . # Terminal output parsing modelfile looking for model ⠋ creating model layer Error: invalid file magic ```` My question: How can I create a model from Modelfile when the model is splitted into multiple .bin files?
GiteaMirror commented 2026-04-12 10:14:03 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Nov 13, 2023):

Hi there, ollama create doesn't yet support loading PyTorch models directly, but you can import using the quantize helper tool: https://github.com/jmorganca/ollama/blob/main/docs/import.md

It will support loading PyTorch models directly in the future, so keep an eye on this issue: https://github.com/jmorganca/ollama/issues/1112

<!-- gh-comment-id:1808703277 --> @jmorganca commented on GitHub (Nov 13, 2023): Hi there, `ollama create` doesn't yet support loading PyTorch models directly, but you can import using the `quantize` helper tool: https://github.com/jmorganca/ollama/blob/main/docs/import.md It will support loading PyTorch models directly in the future, so keep an eye on this issue: https://github.com/jmorganca/ollama/issues/1112
GiteaMirror commented 2026-04-12 10:14:04 -05:00
Author
Owner
Copy Link

@kasperjunge commented on GitHub (Nov 14, 2023):

@jmorganca thanks!

<!-- gh-comment-id:1809646379 --> @kasperjunge commented on GitHub (Nov 14, 2023): @jmorganca thanks!
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#546
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?