Text Generation
Transformers
ONNX
Safetensors
Arabic
English
qwen3
yemenjpt
osint
journalism
arabic
qwen
conversational
Instructions to use Yemen-JPT/WebProcessor-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Yemen-JPT/WebProcessor-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Yemen-JPT/WebProcessor-v1") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Yemen-JPT/WebProcessor-v1") model = AutoModelForCausalLM.from_pretrained("Yemen-JPT/WebProcessor-v1") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Yemen-JPT/WebProcessor-v1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Yemen-JPT/WebProcessor-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/WebProcessor-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Yemen-JPT/WebProcessor-v1
- SGLang
How to use Yemen-JPT/WebProcessor-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/WebProcessor-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/WebProcessor-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/WebProcessor-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/WebProcessor-v1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Yemen-JPT/WebProcessor-v1 with Docker Model Runner:
docker model run hf.co/Yemen-JPT/WebProcessor-v1
Ubuntu commited on
Commit ·
9ee5382
1
Parent(s): d7d1c67
Add bilingual YAML frontmatter and metadata
Browse files
README.md
CHANGED
|
@@ -1,30 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# YemenJPT-WebProcessor-v1
|
| 2 |
|
| 3 |
-
> **معالج
|
| 4 |
|
| 5 |
<div dir="rtl">
|
| 6 |
|
| 7 |
## الوصف
|
| 8 |
-
|
| 9 |
|
| 10 |
-
## ال
|
| 11 |
-
|
| 12 |
-
|
| 13 |
-
|
| 14 |
-
|
| 15 |
-
| الصيغة | ONNX |
|
| 16 |
-
| القاعدة | Huihui-Qwen3-4B-abliterated-v2 |
|
| 17 |
|
| 18 |
## التحميل
|
| 19 |
```bash
|
| 20 |
-
#
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
```
|
| 22 |
|
| 23 |
-
## الر
|
| 24 |
-
|
| 25 |
-
- [منظمة YemenJPT](https://huggingface.co/Yemen-JPT)
|
| 26 |
-
- [RaidanPro](https://raidan.pro)
|
| 27 |
-
- [بيت الصحافة](https://presshouse-ye.com)
|
| 28 |
|
| 29 |
</div>
|
| 30 |
|
|
@@ -32,6 +49,38 @@
|
|
| 32 |
|
| 33 |
<div align="center" dir="rtl">
|
| 34 |
<b>YemenJPT</b> — تمكين الصحافة اليمنية بالذكاء الاصطناعي<br>
|
| 35 |
-
طُوّر بواسطة <a href="https://raidan.pro">RaidanPro</a> بالتعاون مع <a href="https://
|
| 36 |
جميع النماذج متوفرة على <a href="https://huggingface.co/Yemen-JPT">huggingface.co/Yemen-JPT</a>
|
| 37 |
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: text-generation
|
| 3 |
+
library_name: transformers
|
| 4 |
+
tags:
|
| 5 |
+
- yemenjpt
|
| 6 |
+
- osint
|
| 7 |
+
- journalism
|
| 8 |
+
- arabic
|
| 9 |
+
- safetensors
|
| 10 |
+
- qwen
|
| 11 |
+
license: apache-2.0
|
| 12 |
+
language:
|
| 13 |
+
- ar
|
| 14 |
+
- en
|
| 15 |
+
base_model: tomvaillant/qwen-3.5-process-web
|
| 16 |
+
---
|
| 17 |
+
|
| 18 |
# YemenJPT-WebProcessor-v1
|
| 19 |
|
| 20 |
+
> **معالج الويب - لاستخراج وتحليل محتوى المواقع**
|
| 21 |
|
| 22 |
<div dir="rtl">
|
| 23 |
|
| 24 |
## الوصف
|
| 25 |
+
معالج الويب - لاستخراج وتحليل محتوى المواقع. هذا النموذج/القاعدة جزء من مجموعة YemenJPT المخصصة لدعم الصحافة الاستقصائية اليمنية.
|
| 26 |
|
| 27 |
+
## الروابط
|
| 28 |
+
- [المستودع على HuggingFace](https://huggingface.co/Yemen-JPT/OSINT-Web)
|
| 29 |
+
- [منظومة YemenJPT](https://huggingface.co/Yemen-JPT)
|
| 30 |
+
- [RaidanPro](https://raidan.pro)
|
| 31 |
+
- [بيت الصحافة](https://ph-ye.org)
|
|
|
|
|
|
|
| 32 |
|
| 33 |
## التحميل
|
| 34 |
```bash
|
| 35 |
+
# عبر HuggingFace Hub
|
| 36 |
+
git lfs clone https://huggingface.co/Yemen-JPT/OSINT-Web
|
| 37 |
+
|
| 38 |
+
# أو عبر pip (للنماذج)
|
| 39 |
+
pip install huggingface-hub
|
| 40 |
+
huggingface-cli download Yemen-JPT/OSINT-Web
|
| 41 |
```
|
| 42 |
|
| 43 |
+
## الترخيص
|
| 44 |
+
هذا العمل متاح تحت رخصة Apache 2.0 (للنماذج) أو CC-BY-4.0 (لقواعد البيانات).
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
</div>
|
| 47 |
|
|
|
|
| 49 |
|
| 50 |
<div align="center" dir="rtl">
|
| 51 |
<b>YemenJPT</b> — تمكين الصحافة اليمنية بالذكاء الاصطناعي<br>
|
| 52 |
+
طُوّر بواسطة <a href="https://raidan.pro">RaidanPro</a> بالتعاون مع <a href="https://ph-ye.org">بيت الصحافة - Press House</a><br>
|
| 53 |
جميع النماذج متوفرة على <a href="https://huggingface.co/Yemen-JPT">huggingface.co/Yemen-JPT</a>
|
| 54 |
</div>
|
| 55 |
+
|
| 56 |
+
---
|
| 57 |
+
|
| 58 |
+
## YemenJPT-WebProcessor-v1
|
| 59 |
+
|
| 60 |
+
> **Web processor for extracting and analyzing website content**
|
| 61 |
+
|
| 62 |
+
<div>
|
| 63 |
+
|
| 64 |
+
## Description
|
| 65 |
+
Web processor for extracting and analyzing website content. This model/dataset is part of the YemenJPT collection dedicated to supporting Yemeni investigative journalism.
|
| 66 |
+
|
| 67 |
+
## Links
|
| 68 |
+
- [HuggingFace Repository](https://huggingface.co/Yemen-JPT/OSINT-Web)
|
| 69 |
+
- [YemenJPT Ecosystem](https://huggingface.co/Yemen-JPT)
|
| 70 |
+
- [RaidanPro](https://raidan.pro)
|
| 71 |
+
- [Press House](https://ph-ye.org)
|
| 72 |
+
|
| 73 |
+
## Download
|
| 74 |
+
```bash
|
| 75 |
+
# Via HuggingFace Hub
|
| 76 |
+
git lfs clone https://huggingface.co/Yemen-JPT/OSINT-Web
|
| 77 |
+
|
| 78 |
+
# Or via pip (for models)
|
| 79 |
+
pip install huggingface-hub
|
| 80 |
+
huggingface-cli download Yemen-JPT/OSINT-Web
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
+
## License
|
| 84 |
+
This work is licensed under Apache 2.0 (for models) or CC-BY-4.0 (for datasets).
|
| 85 |
+
|
| 86 |
+
</div>
|