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 #14047] Request to add Qalb-1.0-8B-Instruct #71239

New Issue
Closed
opened 2026-05-05 00:51:50 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-05 00:51:50 -05:00
Owner
Copy Link

Originally created by @mwzkhalil on GitHub (Feb 3, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14047

Model Request: Qalb-1.0-8B-Instruct (Urdu LLaMA 3.1)

Model Overview:
Qalb-1.0-8B-Instruct is a state-of-the-art Urdu language model built on the LLaMA-3.1-8B architecture. It has been fine-tuned for instruction-following in Urdu and is designed to bridge the gap in low resource language processing.

Model Source / Repository:

Why This Model is Useful:
Urdu is a low-resource language, and existing multilingual models struggle with grammar, cultural context, and reasoning in Urdu. Qalb provides high-quality, safe, and instruction-following responses, making it ideal for research, AI assistants, translation, and educational tools in Urdu.

Recommended Usage / System Prompt:

آپ ایک مددگار اور بے ضرر مصنوعی ذہانت کے اسسٹنٹ ہیں۔ آپ اردو میں سوالات کے درست جوابات دیتے ہیں۔
Originally created by @mwzkhalil on GitHub (Feb 3, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14047 ## Model Request: Qalb-1.0-8B-Instruct (Urdu LLaMA 3.1) **Model Overview:** Qalb-1.0-8B-Instruct is a state-of-the-art **Urdu language model** built on the LLaMA-3.1-8B architecture. It has been fine-tuned for **instruction-following in Urdu** and is designed to bridge the gap in low resource language processing. **Model Source / Repository:** - Hugging Face: [enstazao/Qalb-1.0-8B-Instruct](https://huggingface.co/enstazao/Qalb-1.0-8B-Instruct) - License: **Unsloth Urdu License** (redistributable) **Why This Model is Useful:** Urdu is a **low-resource language**, and existing multilingual models struggle with grammar, cultural context, and reasoning in Urdu. Qalb provides **high-quality, safe, and instruction-following responses**, making it ideal for research, AI assistants, translation, and educational tools in Urdu. **Recommended Usage / System Prompt:** ```text آپ ایک مددگار اور بے ضرر مصنوعی ذہانت کے اسسٹنٹ ہیں۔ آپ اردو میں سوالات کے درست جوابات دیتے ہیں۔
GiteaMirror added the model label 2026-05-05 00:51:50 -05:00
GiteaMirror commented 2026-05-05 00:52:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 3, 2026):

If it's llama based it can be imported.

<!-- gh-comment-id:3842407915 --> @rick-github commented on GitHub (Feb 3, 2026): If it's llama based it can be [imported](https://github.com/ollama/ollama/blob/main/docs/import.mdx#importing-a-model-from-safetensors-weights).
GiteaMirror commented 2026-05-05 00:52:34 -05:00
Author
Owner
Copy Link

@mwzkhalil commented on GitHub (Feb 3, 2026):

@rick-github Thank you, really appreciate your input.

<!-- gh-comment-id:3843060536 --> @mwzkhalil commented on GitHub (Feb 3, 2026): @rick-github Thank you, really appreciate your input.
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#71239
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?