← back to catalog · registered 2026-08-22 13:56

Matzan/desktop-agent-uncensored

Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/Matzan%2Fdesktop-agent-uncensored"
Response includes
  • classification m-uncensored
  • files 5
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · 30-day
0
Likes
0
Model age
5mo ago
created 2026-05-05
Downloads over time
Now0→from0↑0%
00110 on May 60 on Oct 12MayJunJulAugSepOct
May 6 → Oct 12 · 63 snapshots · spans 159 days

Metadata

Tags
ml-intern region:us
Total size
0 B
Files
5
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-05-05 21:48

Files by quantization

Auxiliary files 5 files 19.6 KB
agent.py 10.3 KB dcdd6ea8 download
train_dpo.py 5.05 KB 75540163 download
README.md 2.62 KB cb2ada73 download
.gitattributes 1.48 KB a6344aac download
requirements.txt 128 B 16dd8987 download

README current version from Hugging Face


tags:

  • ml-intern

🤖 Desktop Agent Autónomo (Sin Censura)

Agente de escritorio autónomo con VLM multimodal sin censura.

Arquitectura

👁️ OJOS     → pyautogui.screenshot() → Captura pantalla
🧠 CEREBRO  → Qwen3.5-35B-A3B-abliterated → Piensa y decide
🖐️ MANOS    → pyautogui → Ejecuta acciones
📚 MEMORIA  → DPO online → Aprende de interacciones

Modelos Soportados (Sin Censura)

Modelo Tamaño VRAM (4-bit) Tipo Link
Qwen3.5-35B-A3B-abliterated ⭐ 35B/3B activos ~16GB MoE HF
Qwen3.6-27B-abliterated 27B ~27GB Dense HF
Gemma-4-26B-A4B-abliterated 26B/4B activos ~14GB MoE HF

Instalación

pip install -r requirements.txt

Uso

1. Ejecutar agente

python agent.py --task "Open Chrome and search for AI news" --steps 20

2. Entrenar con DPO (aprendizaje)

Primero el agente interactúa y guarda logs. Luego:

python train_dpo.py --epochs 3 --lr 5e-7

3. Usar modelo entrenado

python agent.py --model "Matzan/desktop-agent-dpo" --task "New task"

Acciones Soportadas

  • click(x, y) — Click en coordenadas normalizadas (0-1)
  • type("text") — Escribe texto
  • key("enter") — Presiona tecla
  • scroll(x, y, "down") — Scroll en posición
  • done("reason") — Termina tarea
  • fail("reason") — No puede completar

⚠️ Seguridad

  • pyautogui.FAILSAFE = True — Mueve mouse a esquina superior izquierda para abortar
  • El agente puede interactuar con tu desktop real. Úsalo con precaución.

Pipeline de Aprendizaje

1. Agente interactúa → Guarda (screenshot, acción, reward)
2. DPO: compara acciones exitosas vs fallidas
3. Reentrena modelo
4. Repite

Generated by ML Intern

This model repository was generated by ML Intern, an agent for machine learning research and development on the Hugging Face Hub.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = 'Matzan/desktop-agent-uncensored'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

For non-causal architectures, replace AutoModelForCausalLM with the appropriate AutoModel class.

README history 2 versions

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-05-05Update ML Intern artifact metadatac08e4782.6 KB
    Loading...
  2. 2026-05-05Upload README.md with huggingface_hub3b79d2e1.9 KB
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration