github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #2614] AutoModelForCausalLM and .ollama/models #1541

New Issue
Closed
opened 2026-04-12 11:27:04 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 11:27:04 -05:00
Owner
Copy Link

Originally created by @Demirrr on GitHub (Feb 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2614

Can we create an instance of AutoModelForCausalLM from downloaded language models ~/.ollama/models?

By this, the finetunning and using finetuned model via ollama would be easier.

from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "mistralai/Mixtral-8x7B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
Originally created by @Demirrr on GitHub (Feb 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2614 Can we create an instance of `AutoModelForCausalLM` from downloaded language models `~/.ollama/models`? By this, the finetunning and using finetuned model via ollama would be easier. ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id) ```
GiteaMirror commented 2026-04-12 11:27:05 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Feb 20, 2024):

Hi @Demirrr, thanks so much for creating an issue. Check out this doc for instructions on importing PyTorch or Safetensors models (and there's a maintainer that's working on making this much easier).

In the meantime, I know there's quite a few steps, and so let me know if I can help you convert the model at all – my email is in my github profile :)

<!-- gh-comment-id:1954863138 --> @jmorganca commented on GitHub (Feb 20, 2024): Hi @Demirrr, thanks so much for creating an issue. Check out [this doc](https://github.com/jmorganca/ollama/blob/main/docs/import.md) for instructions on importing PyTorch or Safetensors models (and there's a maintainer that's working on making this much easier). In the meantime, I know there's quite a few steps, and so let me know if I can help you convert the model at all – my email is in my github profile :)
GiteaMirror commented 2026-04-12 11:27:06 -05:00
Author
Owner
Copy Link

@categoric-dev commented on GitHub (Jan 6, 2025):

@jmorganca Could we potentially transfer or convert the ollama blob into a model.safetensors format, enabling its utilization alongside AutoModelForCausalLM and AutoTokenizer?

<!-- gh-comment-id:2573785277 --> @categoric-dev commented on GitHub (Jan 6, 2025): @jmorganca Could we potentially transfer or convert the ollama blob into a model.safetensors format, enabling its utilization alongside AutoModelForCausalLM and AutoTokenizer?
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#1541
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?