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 #7781] Llama3.2 Safetensors adapter not supported? #82655

New Issue
Open
opened 2026-05-09 15:27:55 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-09 15:27:55 -05:00
Owner
Copy Link

Originally created by @shuaib7860 on GitHub (Nov 21, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7781

What is the issue?

Hi Guys,

First thanks for creating such a wonderful tool. I have run into a problem which I believe is a bug but I may be incorrect and I could be asking for a feature request. Basically I have fine-tuned a llama3.2 model on some local data and then saved this in safetensors format.

Now I create a model file like below and point it to the safe tensor adapter files. Now when I run the command

ollama create myllama3.2 --file myllama3.2.modelfile

I see the below output which I believe tells me it has been a success.

transferring model data 100%
converting model

But when I run the Ollama list command my newly created model is not displayed. My modelfile starts like the below providing the directory where the safetensors adapter file is stored:

FROM llama3.2:1b
ADAPTER /home/shuaib/tmp/Llama-3.2-1B/

In the Ollama docs and the modelfile markdown file https://github.com/ollama/ollama/blob/main/docs/modelfile.md it says:

Currently supported Safetensor adapters:
Llama (including Llama 2, Llama 3, and Llama 3.1)

Is this why my attempt at creating a model from my fine-tuned model is failing? Because the llama3.2 safetensor adapters are not supported yet? Or am I missing something? Also is there a plan to support the llamam3.2 safentensors adapters anytime soon?

If it is the case because of the lack of support for the llama3.2 safe tensors adapters, should my workaround be to convert my fine-tuned safetensors file into gguf format?

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.4.1

Originally created by @shuaib7860 on GitHub (Nov 21, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7781 ### What is the issue? Hi Guys, First thanks for creating such a wonderful tool. I have run into a problem which I believe is a bug but I may be incorrect and I could be asking for a feature request. Basically I have fine-tuned a llama3.2 model on some local data and then saved this in safetensors format. Now I create a model file like below and point it to the safe tensor adapter files. Now when I run the command ollama create myllama3.2 --file myllama3.2.modelfile I see the below output which I believe tells me it has been a success. transferring model data 100% converting model But when I run the Ollama list command my newly created model is not displayed. My modelfile starts like the below providing the directory where the safetensors adapter file is stored: FROM llama3.2:1b ADAPTER /home/shuaib/tmp/Llama-3.2-1B/ In the Ollama docs and the modelfile markdown file [https://github.com/ollama/ollama/blob/main/docs/modelfile.md](url) it says: Currently supported Safetensor adapters: Llama (including Llama 2, Llama 3, and Llama 3.1) Is this why my attempt at creating a model from my fine-tuned model is failing? Because the llama3.2 safetensor adapters are not supported yet? Or am I missing something? Also is there a plan to support the llamam3.2 safentensors adapters anytime soon? If it is the case because of the lack of support for the llama3.2 safe tensors adapters, should my workaround be to convert my fine-tuned safetensors file into gguf format? ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.4.1
GiteaMirror added the bug label 2026-05-09 15:27:55 -05:00
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 bug
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#82655
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?