Twkeed-GPT-20B (توكيد)

An Arabic language model fine-tuned on Saudi Arabian content, including:

  • Saudi Labor Law articles
  • Saudi dialect understanding
  • Arabic grammar and writing
  • Vision 2030 knowledge

Model Details

  • Base Model: mlx-community/gpt-oss-20b-MXFP4-Q8
  • Fine-tuning Method: LoRA with unsloth-mlx
  • Training Hardware: Mac Studio M3 Ultra 96GB
  • Language: Arabic (Modern Standard + Saudi Dialect)

Model Identity

This model identifies as توكيد (Twkeed) - an Arabic AI assistant.

When asked "من أنت؟" (Who are you?), the model responds with its identity.

Usage

from mlx_lm import load, generate

model, tokenizer = load("twkeed/twkeed-gpt-20b")

response = generate(
    model,
    tokenizer,
    prompt="مرحباً، من أنت؟",
    max_tokens=200,
)
print(response)

Training Data

The model was fine-tuned on:

  • Arabic Alpaca dataset
  • Custom Saudi Labor Law content
  • Saudi dialect examples
  • Arabic grammar instruction data

License

Apache 2.0

Author

Fine-tuned using unsloth-mlx

Downloads last month
34
Safetensors
Model size
21B params
Tensor type
BF16
·
U32
·
U8
·
MLX
Hardware compatibility
Log In to view the estimation

4-bit

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

Model tree for twkeed-sa/twkeed-gpt-20b

Base model

openai/gpt-oss-20b
Quantized
(1)
this model