Instructions to use Yemen-JPT/Editor-Flash-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yemen-JPT/Editor-Flash-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Yemen-JPT/Editor-Flash-v1")
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("Yemen-JPT/Editor-Flash-v1")
model = AutoModelForMultimodalLM.from_pretrained("Yemen-JPT/Editor-Flash-v1")
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 Yemen-JPT/Editor-Flash-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Yemen-JPT/Editor-Flash-v1

SGLang

How to use Yemen-JPT/Editor-Flash-v1 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 "Yemen-JPT/Editor-Flash-v1" \
    --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": "Yemen-JPT/Editor-Flash-v1",
		"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 "Yemen-JPT/Editor-Flash-v1" \
        --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": "Yemen-JPT/Editor-Flash-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Yemen-JPT/Editor-Flash-v1 with Docker Model Runner:
```
docker model run hf.co/Yemen-JPT/Editor-Flash-v1
```

YemenJPT-Editor-Flash-v1

التحرير الصحفي السريع - نموذج متخصص في تحرير النصوص الصحفية

الوصف

التحرير الصحفي السريع - نموذج متخصص في تحرير النصوص الصحفية. هذا النموذج/القاعدة جزء من مجموعة YemenJPT المخصصة لدعم الصحافة الاستقصائية اليمنية.

الروابط

التحميل

# عبر HuggingFace Hub
git lfs clone https://huggingface.co/Yemen-JPT/OSINT-Editor

# أو عبر pip (للنماذج)
pip install huggingface-hub
huggingface-cli download Yemen-JPT/OSINT-Editor

الترخيص

هذا العمل متاح تحت رخصة Apache 2.0 (للنماذج) أو CC-BY-4.0 (لقواعد البيانات).

YemenJPT — تمكين الصحافة اليمنية بالذكاء الاصطناعي
طُوّر بواسطة RaidanPro بالتعاون مع بيت الصحافة - Press House
الموقع الرسمي • فيسبوك • لينكدإن • يوتيوب • HuggingFace • Ollama
yemenjpt@raidan.pro

YemenJPT-Editor-Flash-v1

Fast journalistic editing - specialized in editing journalistic texts

Description

Fast journalistic editing - specialized in editing journalistic texts. This model/dataset is part of the YemenJPT collection dedicated to supporting Yemeni investigative journalism.

Download

# Via HuggingFace Hub
git lfs clone https://huggingface.co/Yemen-JPT/OSINT-Editor

# Or via pip (for models)
pip install huggingface-hub
huggingface-cli download Yemen-JPT/OSINT-Editor

License

This work is licensed under Apache 2.0 (for models) or CC-BY-4.0 (for datasets).

Downloads last month: 6

Safetensors

Model size

8B params

Tensor type

BF16

Yemen-JPT
/

Editor-Flash-v1

YemenJPT-Editor-Flash-v1

الوصف

الروابط

التحميل

الترخيص

YemenJPT-Editor-Flash-v1

Description

Links

Download

License