github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 04:34:16 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7147] Support for GrabbeAI #4536

New Issue
Open
opened 2026-04-12 15:28:28 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-12 15:28:28 -05:00
Owner
Copy Link

Originally created by @finnbusse on GitHub (Oct 9, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7147

GrabbeAI is an AI model trained by 10th grade students of the german grammar school Grabbe-Gymnasium Detmold and helps users - especially students and teachers - with their (home)work! From what I know, it is the first LLM made entirely by students!
Since I personally trained the model with some other students with the (financial) assistance from some teachers, you can find the model both on Hugging Face and Ollama Model Hub.
The Hugging Face URL is: https://huggingface.co/grabbe-gymnasium-detmold/grabbe-ai
The Ollama hub URL is: https://ollama.com/grabbe-gymnasium/grabbe-ai

On Hugging Face, the model has about 9 million downloads, on Ollama hub it has more then 300, so I think it could be relevant for a huge group of people!
We trained the model based on real class test tasks and good homeworks and it works quiet fine. We are actively updating our LLM on Hugging Face and plan to publish a new build until December. This new release will double the trained dataset!

Originally created by @finnbusse on GitHub (Oct 9, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7147 GrabbeAI is an AI model trained by 10th grade students of the german grammar school Grabbe-Gymnasium Detmold and helps users - especially students and teachers - with their (home)work! From what I know, it is the first LLM made entirely by students! Since I personally trained the model with some other students with the (financial) assistance from some teachers, you can find the model both on Hugging Face and Ollama Model Hub. The Hugging Face URL is: https://huggingface.co/grabbe-gymnasium-detmold/grabbe-ai The Ollama hub URL is: https://ollama.com/grabbe-gymnasium/grabbe-ai On Hugging Face, the model has about 9 million downloads, on Ollama hub it has more then 300, so I think it could be relevant for a huge group of people! We trained the model based on real class test tasks and good homeworks and it works quiet fine. We are actively updating our LLM on Hugging Face and plan to publish a new build until December. This new release will double the trained dataset!
GiteaMirror added the model label 2026-04-12 15:28:28 -05:00
GiteaMirror commented 2026-04-12 15:28:30 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 9, 2024):

The link to the dataset from the model card is broken - trailing %5D.

<!-- gh-comment-id:2402065408 --> @rick-github commented on GitHub (Oct 9, 2024): The link to the dataset from the model card is broken - trailing %5D.
GiteaMirror commented 2026-04-12 15:28:31 -05:00
Author
Owner
Copy Link

@finnbusse commented on GitHub (Oct 9, 2024):

@rick-github It works for me...

<!-- gh-comment-id:2402093943 --> @finnbusse commented on GitHub (Oct 9, 2024): @rick-github It works for me...
GiteaMirror commented 2026-04-12 15:28:31 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 9, 2024):

Screenshot 2024-10-09 13 56 47

<!-- gh-comment-id:2402119428 --> @rick-github commented on GitHub (Oct 9, 2024): ![Screenshot 2024-10-09 13 56 47](https://github.com/user-attachments/assets/f19b0f72-a25f-4c07-bb40-82436007bf20)
GiteaMirror commented 2026-04-12 15:28:32 -05:00
Author
Owner
Copy Link

@finnbusse commented on GitHub (Oct 9, 2024):

@rick-github I don't know why this is there... but this URL is working: https://huggingface.co/datasets/grabbe-gymnasium-detmold/grabbeai
grafik

<!-- gh-comment-id:2402123727 --> @finnbusse commented on GitHub (Oct 9, 2024): @rick-github I don't know why this is there... but this URL is working: https://huggingface.co/datasets/grabbe-gymnasium-detmold/grabbeai ![grafik](https://github.com/user-attachments/assets/3e5b1670-b982-4e3a-b8ee-93f63b7202cb)
GiteaMirror commented 2026-04-12 15:28:32 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 9, 2024):

This link, not the one on the right hand side.

Screenshot 2024-10-09 14 03 59

<!-- gh-comment-id:2402133212 --> @rick-github commented on GitHub (Oct 9, 2024): This link, not the one on the right hand side. ![Screenshot 2024-10-09 14 03 59](https://github.com/user-attachments/assets/cffe9b41-c442-4ef8-be75-82a4f2d18028)
GiteaMirror commented 2026-04-12 15:28:33 -05:00
Author
Owner
Copy Link

@finnbusse commented on GitHub (Oct 9, 2024):

Oh this is the same link and the same dataset. But I will try to fix it!

Edit: @rick-github I fixed the problem: it was just the square bracket which added the %5D

<!-- gh-comment-id:2402135922 --> @finnbusse commented on GitHub (Oct 9, 2024): Oh this is the same link and the same dataset. But I will try to fix it! Edit: @rick-github I fixed the problem: it was just the square bracket which added the %5D
GiteaMirror commented 2026-04-12 15:28:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 9, 2024):

I see you also finetuned qwen2.5 and llama3.1. Did you find substantial differences between the different models?

<!-- gh-comment-id:2402147993 --> @rick-github commented on GitHub (Oct 9, 2024): I see you also finetuned qwen2.5 and llama3.1. Did you find substantial differences between the different models?
GiteaMirror commented 2026-04-12 15:28:33 -05:00
Author
Owner
Copy Link

@finnbusse commented on GitHub (Oct 9, 2024):

Yes. Those models are experiencing much halluscination, I think this is because of the low amout of parameters the base model was trained with. I am currently working on training the Mistral models. If those give better results, we might change this in the future. But the main differences between qwen2.5 and llama3.1 I noticed was qwen2-5's lower accuracy for other languages than English and Chinese. Llama 3.1 did this quiet well. But both llama 3.1 and qwen2.5 have a huge difference to what gemma2 or the Mistral models (v0.3 7b and Mistral Nemo) offer.

<!-- gh-comment-id:2402160708 --> @finnbusse commented on GitHub (Oct 9, 2024): Yes. Those models are experiencing much halluscination, I think this is because of the low amout of parameters the base model was trained with. I am currently working on training the Mistral models. If those give better results, we might change this in the future. But the main differences between qwen2.5 and llama3.1 I noticed was qwen2-5's lower accuracy for other languages than English and Chinese. Llama 3.1 did this quiet well. But both llama 3.1 and qwen2.5 have a huge difference to what gemma2 or the Mistral models (v0.3 7b and Mistral Nemo) offer.
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 model
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#4536
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?