tawkeed-gpt

Model Details

Tawkeed Notes

This checkpoint is a direct Tawkeed-branded fork of Nex-N2-mini and should be described as on top of Qwen3.5 through the upstream Nex-N2-mini lineage.

No additional Tawkeed post-training checkpoint has been uploaded on top of this fork yet. If Tawkeed later performs additional SFT or continued post-training, upload the resulting adapter or merged checkpoint to this same repository and update this card with the training details.

Usage

python
Copy code
from transformers import AutoModelForMultimodalLM, AutoProcessor

processor = AutoProcessor.from_pretrained("tawkeed-sa/tawkeed-gpt")
model = AutoModelForMultimodalLM.from_pretrained("tawkeed-sa/tawkeed-gpt")

messages = [
    {"role": "user", "content": "اكتب ملخصا قصيرا عن رؤية السعودية 2030."},
]
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=512)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Attribution

Checkpoint weights are forked from nex-agi/Nex-N2-mini by Nex AGI. Tawkeed maintains this renamed fork for Tawkeed workflows.