Instructions to use HabibaAbdeldayem/taa-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use HabibaAbdeldayem/taa-models with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HabibaAbdeldayem/taa-models
# Run inference directly in the terminal:
llama cli -hf HabibaAbdeldayem/taa-models

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf HabibaAbdeldayem/taa-models
# Run inference directly in the terminal:
llama cli -hf HabibaAbdeldayem/taa-models

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf HabibaAbdeldayem/taa-models
# Run inference directly in the terminal:
./llama-cli -hf HabibaAbdeldayem/taa-models

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf HabibaAbdeldayem/taa-models
# Run inference directly in the terminal:
./build/bin/llama-cli -hf HabibaAbdeldayem/taa-models

Use Docker

docker model run hf.co/HabibaAbdeldayem/taa-models

LM Studio
Jan
Ollama
How to use HabibaAbdeldayem/taa-models with Ollama:
```
ollama run hf.co/HabibaAbdeldayem/taa-models
```
Unsloth Desktop

How to use HabibaAbdeldayem/taa-models with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HabibaAbdeldayem/taa-models

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "HabibaAbdeldayem/taa-models"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use HabibaAbdeldayem/taa-models with Docker Model Runner:
```
docker model run hf.co/HabibaAbdeldayem/taa-models
```

Lemonade

How to use HabibaAbdeldayem/taa-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull HabibaAbdeldayem/taa-models

Run and chat with the model

lemonade run user.taa-models-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use HabibaAbdeldayem/taa-models with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HabibaAbdeldayem/taa-models

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default HabibaAbdeldayem/taa-models

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use HabibaAbdeldayem/taa-models with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf HabibaAbdeldayem/taa-models

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "HabibaAbdeldayem/taa-models" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

taa3-q40 — تاء: استخراج المهام من الجمل العربية

Qwen3.5-0.8B متدرب بـ LoRA (الجولة 3)، ومضغوط Q4_0 (489 ميجا). بياخد جملة بأي لهجة عربية ويطلّع المهام بصيغة مختصرة، كل مهمة في سطر:

شراء عيش;d=1;pt=morning;c=shopping
شراء الدوا;d=1;pt=morning;p=أحمد;c=health

لو مفيش مهام، الرد بيبقى -.

البرومبت

Raw ChatML من غير وضع التفكير. التوليد greedy، و repeat penalty 1.0، والتوقف عند <|im_end|>:

<|im_start|>system
استخرج المهام من رسالة المستخدم.<|im_end|>
<|im_start|>user
{الجملة}<|im_end|>
<|im_start|>assistant

الأرقام

دقة الحقول 92.7% على 137 جملة اختبار.
على Galaxy A34 (CPU بـ 2 threads): الوسيط حوالي 1.7 ثانية للجملة.

Downloads last month: 202

GGUF

Model size

0.8B params

Architecture

qwen35

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for HabibaAbdeldayem/taa-models

Base model

Qwen/Qwen3.5-0.8B-Base

Finetuned

Qwen/Qwen3.5-0.8B

Quantized

(316)

this model