← back to catalog · registered 2026-09-27 20:57

blaj/Qwen2.5-VL-7B-Instruct-abliterated-int8-ov

blaj 7B multimodal second-order
curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/blaj%2FQwen2.5-VL-7B-Instruct-abliterated-int8-ov"
Response includes
  • classification m-uncensored
  • files 21
  • author_summary 10 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
today
created 2026-09-27

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
Tags
openvino qwen2_5_vl int8 qwen2.5-vl vlm abliterated uncensored intel arc image-text-to-text conversational base_model:huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated

Related

Total size
8.87 GB
Files
21
Quantizations
1
Registered
2026-09-27 20:57
Last updated on HF
2026-09-27 20:11

Files by quantization

Auxiliary files 21 files 8.89 GB
openvino_language_model.bin 6.59 GB 64be1c5a download
openvino_vision_embeddings_merger_model.bin 1.26 GB 76e717e3 download
openvino_text_embeddings_model.bin 1.02 GB afa5a3cb download
openvino_tokenizer.bin 5.33 MB 1a86fe0e download
openvino_vision_embeddings_model.bin 2.87 MB 5ced73d8 download
openvino_detokenizer.bin 2.09 MB 3ca47601 download
tokenizer.json 10.9 MB 3fd16973 download
openvino_language_model.xml 2.62 MB 137ca606 download
openvino_vision_embeddings_merger_model.xml 1.73 MB 47d34f27 download
openvino_tokenizer.xml 26.4 KB 829a02a9 download
openvino_detokenizer.xml 9.58 KB d34acb6f download
openvino_vision_embeddings_model.xml 4.75 KB e478b9b2 download
openvino_text_embeddings_model.xml 3.22 KB 10933b89 download
README.md 2.81 KB 136426af download
config.json 2.32 KB 77da0722 download
.gitattributes 1.53 KB 52373fe2 download
processor_config.json 1.39 KB 9e717d9b download
chat_template.jinja 1017 B 6c226632 download
tokenizer_config.json 708 B a32ee6b0 download
preprocessor_config.json 522 B 5a1d164c download
generation_config.json 213 B 0abe783c download

README current version from Hugging Face


library_name: openvino
license: apache-2.0
base_model:

  • huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated
    pipeline_tag: image-text-to-text
    tags:
  • openvino
  • int8
  • qwen2.5-vl
  • vlm
  • abliterated
  • uncensored
  • intel
  • arc

Qwen2.5-VL-7B-Instruct-abliterated — OpenVINO IR (int8)

OpenVINO IR conversion of
huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated,
an abliterated (decensored) build of Qwen2.5-VL-7B-Instruct.

This is a full VLM export: vision tower, vision-language merger, text embeddings,
language model, tokenizer and detokenizer are all present.

Sibling build: int4

Details

Property Value
Architecture Qwen2_5_VLForConditionalGeneration, 28 text layers, hidden 3584
Format OpenVINO IR, int8 asymmetric per-channel
Repository size 9.3 GB
Export type decomposed VLM (separate vision / merger / text-embedding graphs)

Because the text graph has more than the two inputs LLMPipeline expects, load this
through VLMPipeline, or serve it with OVMS which dispatches automatically.

Benchmark

Intel Core Ultra 7 258V (Arc 130V/140V iGPU), 30 GB RAM, OpenVINO Model Server
2026.4.0 on GPU, greedy decoding, 128 max new tokens, mean of 3 runs.

Build tok/s
int4 22.6
int8 (this build) 13.0

Decode here is memory-bandwidth bound, so throughput tracks model size closely.

Serving

cat > ovms_config.json <<'EOF'
{
  "model_config_list": [
    {
      "config": {
        "name": "qwen2.5-vl",
        "base_path": "/absolute/path/to/this/model",
        "target_device": "GPU",
        "nireq": 8,
        "plugin_config": { "PERFORMANCE_HINT": "THROUGHPUT", "NUM_STREAMS": "2" }
      }
    }
  ]
}
EOF

# graph.pbtxt must also exist in the model directory.
PYTHONPATH=$OVMS_ROOT/lib/python ovms --config_path ./ovms_config.json --rest_port 11436

Conversion notes

  • Stage 1: optimum-cli export openvino --task image-text-to-text --weight-format fp16
  • Stage 2: nncf.compress_weights on the language-model IR.
  • Requires transformers 5.0 — the qwen2_5_vl exporter rejects newer versions
    (MAX_TRANSFORMERS_VERSION = "5.0"). Newer transformers fails with a version-gate error.
  • optimum-intel 2.2.0 / OpenVINO 2026.4.0.

Limitations

  • Abliterated: reduced refusal behavior. Evaluate outputs before deployment.
  • Quantized; re-export at a smaller group size or fp16 for maximum accuracy.
  • Throughput depends on runtime kernels, hardware, and prompt distribution.

Attribution

Base model: huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated.
Qwen2.5-VL is Apache-2.0. Conversion via optimum-intel + NNCF.

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.