Instructions to use tawkeed-sa/tawkeed-gpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tawkeed-sa/tawkeed-gpt with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="tawkeed-sa/tawkeed-gpt")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("tawkeed-sa/tawkeed-gpt")
model = AutoModelForMultimodalLM.from_pretrained("tawkeed-sa/tawkeed-gpt")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tawkeed-sa/tawkeed-gpt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tawkeed-sa/tawkeed-gpt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tawkeed-sa/tawkeed-gpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tawkeed-sa/tawkeed-gpt

SGLang

How to use tawkeed-sa/tawkeed-gpt 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 "tawkeed-sa/tawkeed-gpt" \
    --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": "tawkeed-sa/tawkeed-gpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "tawkeed-sa/tawkeed-gpt" \
        --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": "tawkeed-sa/tawkeed-gpt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tawkeed-sa/tawkeed-gpt with Docker Model Runner:
```
docker model run hf.co/tawkeed-sa/tawkeed-gpt
```

Tawkeed GPT

Tawkeed GPT is a Tawkeed-branded fork of nex-agi/Nex-N2-mini.

The upstream Nex-N2 model card states that Nex-N2-mini is built on Qwen3.5-35B-A3B-Base. This repository keeps that lineage explicit while providing the Tawkeed GPT model name.

Model Details

Property	Value
Name	Tawkeed GPT
Repository	tawkeed-sa/tawkeed-gpt
Upstream Model	nex-agi/Nex-N2-mini
Upstream Base Lineage	`Qwen3.5-35B-A3B-Base`
Architecture	Qwen3.5 MoE / qwen3_5_moe
License	Apache 2.0

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

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.

Downloads last month: 83

Safetensors

Model size

35B params

Tensor type

BF16

Model tree for tawkeed-sa/tawkeed-gpt

Base model

nex-agi/Nex-N2-mini

Finetuned

(7)

this model