← back to catalog · registered 2026-11-19 21:04

draganjankovic1975/Gliese-Qwen3.5-9B-Abliterated-Caption

draganjankovic1975 Qwen 9B multimodal
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/draganjankovic1975%2FGliese-Qwen3.5-9B-Abliterated-Caption"
Response includes
  • classification m1
  • files 12
  • benchmarks 11 entries
  • author_summary 7 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • 'abliterated' in name/tags
  • is_gguf=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
23
Likes
0
Model age
2d ago
created 2026-11-19
Downloads over time
Now 23 → from 0 ↑ 0%
081725 0 on Nov 19 23 on Nov 22 Nov
Nov 19 → Nov 22 · 4 snapshots · spans 3 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 1.4 UGI
Hazardous 2.4 UGI
Natural Intelligence 17.62 UGI
Political lean -12.2% UGI
Sensitive-Info 14.65 UGI
SocPol 0.9 UGI
UGI 17.27 UGI
Willingness (10) 2.2 UGI
W10-Adherence 1.5 UGI
W10-Direct 3 UGI
Writing 33.52 UGI

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
apache-2.0
Languages
en zh
Tags
transformers safetensors qwen3_5 image-text-to-text text-generation-inference pytorch uncensored abliterated unfiltered unredacted refusal-ablated vllm

Related

Total size
17.5 GB
Files
12
Quantizations
1
Registered
2026-11-19 21:04
Last updated on HF
2026-11-19 20:12

Files by quantization

Auxiliary files 12 files 17.5 GB
model-00001-of-00003.safetensors 8.75 GB 09b1fe49 download
model-00002-of-00003.safetensors 8.74 GB 28446160 download
model-00003-of-00003.safetensors 44.4 MB 0123786d download
tokenizer.json 19.1 MB 87a7830d download
model.safetensors.index.json 67.6 KB 9decf4be download
chat_template.jinja 12.0 KB 3a5c99d4 download
README.md 7.75 KB cd11d91e download
config.json 2.76 KB 56c5e94f download
.gitattributes 2.25 KB 1d79738f download
processor_config.json 1.27 KB 7ad6acdf download
tokenizer_config.json 1.11 KB 541f6c47 download
generation_config.json 120 B 19800364 download

README current version from Hugging Face


license: apache-2.0
tags:

  • text-generation-inference
  • pytorch
  • uncensored
  • abliterated
  • unfiltered
  • unredacted
  • refusal-ablated
  • vllm
  • bf16
  • max
  • alignment-modified
  • reasoning
    language:
  • en
  • zh
    base_model:
  • Qwen/Qwen3.5-9B
    pipeline_tag: image-text-to-text
    library_name: transformers

Mirror of prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption. License: apache-2.0. All credit to the original author.

1

Gliese-Qwen3.5-9B-Abliterated-Caption

Gliese-Qwen3.5-9B-Abliterated-Caption is an abliterated evolution built on top of Qwen/Qwen3.5-9B, designed specifically for generalized and unfiltered image captioning. The model applies advanced refusal direction analysis and abliterated training strategies to minimize internal refusal behaviors while maximizing descriptive capability and visual understanding. The result is a powerful 9B parameter vision-language model optimized for highly detailed captions, deep scene understanding, and rich visual descriptions.

[!IMPORTANT]
This model is materialized for research and learning purposes only. The model has reduced internal refusal behaviors, and any content generated by it is used at the user’s own risk. The authors and hosting page disclaim any liability for content generated by this model. Users are responsible for ensuring that the model is used in a a safe, ethical, and lawful manner.

Get GGUF
File Name Quant Type File Size File Link
Gliese-Qwen3.5-9B-Abliterated-Caption.BF16.gguf BF16 17.9 GB Download
Gliese-Qwen3.5-9B-Abliterated-Caption.F16.gguf F16 17.9 GB Download
Gliese-Qwen3.5-9B-Abliterated-Caption.F32.gguf F32 35.8 GB Download
Gliese-Qwen3.5-9B-Abliterated-Caption.Q8_0.gguf Q8_0 9.53 GB Download
Gliese-Qwen3.5-9B-Abliterated-Caption.mmproj-bf16.gguf mmproj-bf16 922 MB Download
Gliese-Qwen3.5-9B-Abliterated-Caption.mmproj-f16.gguf mmproj-f16 922 MB Download
Gliese-Qwen3.5-9B-Abliterated-Caption.mmproj-f32.gguf mmproj-f32 1.82 GB Download
Gliese-Qwen3.5-9B-Abliterated-Caption.mmproj-q8_0.gguf mmproj-q8_0 624 MB Download

[!NOTE]
Expert Image Captioning System (chat_template.jinja) –
https://huggingface.co/prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption/blob/main/chat_template.jinja
[Recommended]

[!NOTE]
Standard or Default (chat_template.jinja) –
https://huggingface.co/prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption/blob/main/standard-chat_template/chat_template.jinja


Base Model Signatures:

This model has been re-sharded and optimized for the latest Transformers version from the base model: https://huggingface.co/huihui-ai/Huihui-Qwen3.5-9B-abliterated.


Download the model

hf auth login --token <YOUR_HF_TOKEN>

hf download prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption

Key Highlights

  • Advanced Refusal Direction Analysis
    Uses targeted activation analysis to identify and mitigate refusal directions within the model’s latent space.

  • Abliterated Caption Training
    Fine-tuned for unfiltered and detailed caption generation, enabling comprehensive visual descriptions without excessive refusal behaviors.

  • Optimized Visual Understanding
    Enhanced to provide rich, context-aware descriptions of scenes, objects, people, and environments.

  • 9B Parameter Architecture
    Built on Qwen3.5-9B, delivering strong multimodal reasoning and improved caption quality while remaining deployable on modern GPUs.

  • High-Fidelity Caption Generation
    Designed to produce long-form, structured, and semantically detailed captions suitable for dataset generation, annotation, and research.

  • Efficient Deployment
    Suitable for caption dataset creation, multimodal research, local inference pipelines, and AI development workflows.

Quick Start with Transformers

pip install transformers==5.3.0
# or
pip install git+https://github.com/huggingface/transformers.git
from transformers import Qwen3_5ForConditionalGeneration, AutoProcessor
import torch

model = Qwen3_5ForConditionalGeneration.from_pretrained(
    "prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption",
    torch_dtype="auto",
    device_map="auto"
)

processor = AutoProcessor.from_pretrained(
    "prithivMLmods/Gliese-Qwen3.5-9B-Abliterated-Caption"
)

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Describe this image in extreme detail."}
        ],
    }
]

text = processor.apply_chat_template(
    messages, tokenize=False, add_generation_prompt=True
)

inputs = processor(
    text=[text],
    padding=True,
    return_tensors="pt"
).to("cuda")

generated_ids = model.generate(**inputs, max_new_tokens=512)

generated_ids_trimmed = [
    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
]

output_text = processor.batch_decode(
    generated_ids_trimmed,
    skip_special_tokens=True,
    clean_up_tokenization_spaces=False
)

print(output_text)

Intended Use

  • High-Detail Image Captioning – Generating extremely descriptive captions for images.
  • Dataset Generation – Creating large-scale caption datasets for multimodal training.
  • Vision-Language Research – Studying multimodal reasoning and captioning behavior.
  • Annotation Automation – Assisting in automatic labeling and visual description tasks.
  • Local Multimodal AI Deployment – Running powerful captioning models on local GPUs.

Limitations & Risks

Important Note: This model intentionally reduces built-in refusal mechanisms.

  • Unfiltered Outputs – The model may generate explicit or controversial captions depending on the input images.
  • User Responsibility – Generated outputs should be handled responsibly and within legal and ethical boundaries.
  • Model Size Constraints – While strong, a 9B model still has limitations compared to frontier-scale multimodal architectures.

README history 1 version

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

  1. 2026-11-19 Upload folder using huggingface_hub 6e4d1bc 7.8 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