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

Libraries

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
```

WebProcessor-v1 / README.md

Ameen

Upload OSINT-Web - Web-based ONNX model for in-browser inference (14GB)

d14e3e8 verified about 2 months ago

3.02 kB

license: apache-2.0
base_model: huihui-ai/Huihui-Qwen3-4B-abliterated-v2
language:
  - en
tags:
  - onnx
  - qwen3
  - transformers.js
  - webgpu
  - investigative-journalism
  - osint
  - conversational

qwen3-4b-abliterated-v2-journalist-ONNX

ONNX/WebGPU export of tomvaillant/qwen3-4b-abliterated-v2-journalist, a compact investigative journalism and OSINT fine-tune based on huihui-ai/Huihui-Qwen3-4B-abliterated-v2.

This repo is intended for local browser inference with Transformers.js and WebGPU.

Usage

import { AutoTokenizer, AutoModelForCausalLM } from "@huggingface/transformers";

const modelId = "tomvaillant/qwen3-4b-abliterated-v2-journalist-ONNX";
const tokenizer = await AutoTokenizer.from_pretrained(modelId);
const model = await AutoModelForCausalLM.from_pretrained(modelId, {
  dtype: "q4",
  device: "webgpu",
});

const messages = [
  { role: "user", content: "What records should I check to verify who owns a local company?" },
];

const inputs = tokenizer.apply_chat_template(messages, {
  add_generation_prompt: true,
  return_dict: true,
  enable_thinking: false,
});

const output = await model.generate({ ...inputs, max_new_tokens: 512 });
console.log(tokenizer.decode(output[0], { skip_special_tokens: true }));

Files

onnx/model_q4.onnx
onnx/model_q4.onnx_data*
genai_config.json
tokenizer and chat-template files

Training And Conversion

Adapter: tomvaillant/qwen3-4b-abliterated-v2-journalist
Merged checkpoint: tomvaillant/qwen3-4b-abliterated-v2-journalist-merged
Training: QLoRA with Unsloth + TRL SFT
ONNX export: onnxruntime-genai int4 export with external data split for browser loading
Dataset: tomvaillant/investigative-journalism-training

Sources And Attribution

Training data covers OSINT tool selection, verification methodology, financial investigation, digital security, sourcing, media law, ethics, and investigative writing.

Key sources include tomvaillant/osint-tool-database, Indicator Media briefing tools, Buried Signals skill repositories, GIJN resources, Bellingcat guides, Verification Handbook 3, SPJ Code of Ethics, RCFP resources, and public investigative manuals from UNESCO, Al Jazeera Media Institute, CiFAR, CIPE, and EJF/TEMPO Institute.

Full attribution is maintained in the training repository as SOURCES.md.

Intended Use

Built for in-browser investigative assistance in OSINT workflows. Treat generated tool recommendations, URLs, and factual claims as research leads requiring independent verification.