Instructions to use anaspro/Shako-iraqi-4B-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anaspro/Shako-iraqi-4B-it with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="anaspro/Shako-iraqi-4B-it") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("anaspro/Shako-iraqi-4B-it") model = AutoModelForMultimodalLM.from_pretrained("anaspro/Shako-iraqi-4B-it", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use anaspro/Shako-iraqi-4B-it with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "anaspro/Shako-iraqi-4B-it" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "anaspro/Shako-iraqi-4B-it", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/anaspro/Shako-iraqi-4B-it
- SGLang
How to use anaspro/Shako-iraqi-4B-it with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "anaspro/Shako-iraqi-4B-it" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "anaspro/Shako-iraqi-4B-it", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "anaspro/Shako-iraqi-4B-it" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "anaspro/Shako-iraqi-4B-it", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Unsloth Desktop
- Docker Model Runner
How to use anaspro/Shako-iraqi-4B-it with Docker Model Runner:
docker model run hf.co/anaspro/Shako-iraqi-4B-it
Shako-n โ Advanced Iraqi Dialect Finetuned Model
- Developed by: anaspro
- License: apache-2.0
- Finetuned from model: unsloth/gemma-3n-E4B-it
Shako-n (ุดูู AI / Shako-n Model) is a specialized Iraqi Arabic LLM designed to produce natural, authentic Iraqi dialect with cultural understanding, humor, and accurate social expressions.
Built on Gemma-3n and optimized using Unsloth, it delivers fast training, high efficiency, and natural Iraqi-style responses for chatbots, assistants, and customer-service applications.
This model accurately understands Iraqi slang, social context, professional tone, and mixed Arabic-English messaging.
๐ง Model Overview
Shako-n specializes in:
- Conversational Iraqi dialect (ููุฌุฉ ุนุฑุงููุฉ ุฏุงุฑุฌุฉ)
- Real social expressions (ูุง ุดููุ ุดูู ุงูุณุงููุฉุ)
- Polite and professional support responses
- Mixed ArabicโEnglish use
- Understanding Iraqi culture, humor, and tone
- Province-based variations in language
Designed for:
- Iraqi AI chatbots
- Iraqi virtual agents
- Customer-service AI
- Support centers & business tools
- Iraqi content generation
- Research on dialects
๐ Key Features
โ 1. Natural Iraqi Dialect
Generates smooth, real-life phrases like:
- โูุง ุญุจู ุดูู ู ุงููุโ
- โูู ูู ุงูุช ูููุ ุตุงุฑูู ููู ูู ู ุฎุชูู!โ
- โูุง ุญุจูุจู ู ู ฺููุ ุงูุณุงููุฉ ุชุฎุชูู.โ
- โุชุฑู ุงูู ูุถูุน ููู ุจุณูุทุ ุฎู ุงูุถุญูู.โ
โ 2. Formal + Informal Tone Switching
Informal example:
- โููุง ุจุงูุบุงููุ ุดุชุฑูุฏ ุงุณุงุนุฏูุโ
Semi-professional:
- โุตุฏููู ุงูุนุฒูุฒุ ุฎูููู ุงุดูููู ุงูู ุดููุฉ.โ
Professional:
- โุนุฒูุฒู ุงูุนู ููุ ูุฑุฌู ุชุฒููุฏูุง ุจุงูุชูุงุตูู ุญุชู ููุฏุฑ ููู ู ุงูุฅุฌุฑุงุก.โ
โ 3. Customer Support Quality
Optimized for:
- Troubleshooting
- Step-by-step instructions
- Apology and clarification tone
Example:
- โูุนุชุฐุฑ ู ูู ุนูู ุงูุฅุฒุนุงุฌุ ุฎู ูุฌุฑุจ ูุนูุฏ ุชุดุบูู ุงูุฎุฏู ุฉ ููุดูู ูุชุญุณู ุงููุถุน.โ
โ 4. Cultural Understanding
Knows Iraqi cultural references:
- โูุงู ุณุงููุฉ ู ู ุฃูุงู ุงูุจุตุฑุฉ ุงููุฏูู ุฉ.โ
- โุงูู ูุตู ุฅููุง ูููุฉ ุฎุงุตุฉ ุจุงูุญุฌู.โ
๐ฆ Technical Details
| Property | Value |
|---|---|
| Base Model | unsloth/gemma-3n-E4B-it |
| Architecture | Gemma-3n |
| Model Size | 4B parameter class |
| Context Window | ~4096 tokens |
| Training Method | SFT (Supervised Fine-Tuning) |
| Frameworks | Unsloth + TRL |
| Languages | Iraqi Arabic, Arabic (MSA), English |
๐ Training Data
The finetuning dataset was fully customized and included:
1. Iraqi Informal Conversations
- ููู ูุงุช
- ุณูุงูู ุฃุตุฏูุงุก
- ููุฌุฉ ุฏุงุฑุฌุฉ ุณุฑูุนุฉ
- ููู ุงุช ู ุณุชุนู ูุฉ ุจุงูุนุฑุงู ููู ููุง
Example lines used:
- โูุณู ุงุฌูุชุ ููููู ุจูุณุโ
- โุชุฑู ุงูุฌู ุงูููู ู ุทุจูุนู.โ
2. Support / Call-Center Dialogues
- Account issues
- Network problems
- Delivery, orders, complaints
Examples:
- โุชุฏููุ ุฑุงุญ ุงุชุฃูุฏ ู ู ุญุณุงุจู ูุณู.โ
- โูุนุชุฐุฑ ู ููุ ุงูุณูุฑูุฑ ูุงู ุนููู ุถุบุท.โ
3. Iraqi Cultural Content
Includes:
- ุงูู ุญุงูุธุงุช
- ุงูุฃู ุซุงู
- ุงูุนุงุฏุงุช ูุงูุชูุงููุฏ
- ุงูููุฌุงุช ุงููุฑุนูุฉ
Examples:
- โู ุซู ู ุง ูููููู: ุงูู ุงูุดูู ู ู ุงูุบุฑุจุงู ุงุนู ู.โ
- โูุฐู ุฃููุฉ ู ุดููุฑุฉ ุจุงูุจุตุฑุฉ ุงุณู ูุง โู ุฑู ุจุงุฌูุงโ.โ
4. Mixed ArabicโEnglish
To handle modern chat flow:
- โุงููู ุญุจู ุฏุฒูู screenshot ุญุชู ุงุดูู.โ
- โRestart ููุฑุงูุชุฑ ูุฌุฑุจ ุจุนุฏ ูฃ ุฏูุงูู.โ
5. JSONL Format
{"conversations":[
{"from": "human", "value": "ูุง ุดูู ุงูููู
ุ"},
{"from": "gpt", "value": "ููุง ุญุจูุ ุงูุฃู
ูุฑ ุชู
ุงู
. ุงูุช ุดุฎุจุงุฑูุ"}
]}
- Downloads last month
- 77