Downloads · 30 days
157
81% of all-time downloads
saracen9/qwen3vl-4b-krea2-abliterated
qwen3vl-4b-krea2-abliterated is a image-text-to-text model from saracen9. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
A refusal-removed ("abliterated") copy of Qwen/Qwen3-VL-4B-Instruct, produced with Heretic.
Downloads · 30 days
157
81% of all-time downloads
All-time downloads
194
Public
Parameters
4.4B
26.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors26.6 GB · 100%
From the Hugging Face model README
A refusal-removed ("abliterated") copy of Qwen/Qwen3-VL-4B-Instruct, produced with Heretic.
Krea2 (an image-generation model) uses Qwen3-VL-4B as its frozen text/CLIP encoder — Krea2's own prompt adherence depends entirely on that encoder's internal representations, across both its TextGenerate prompt-refinement path and its CLIPTextEncode embedding-conditioning path. Alignment training suppresses how restricted content is represented internally, not just how it's generated — this checkpoint removes that suppression via the same single-pass Heretic technique already validated for this project's own production Qwen3.5-9B base (ADR-004).
This is a drop-in replacement for Krea2's own qwen3vl_4b_fp8_scaled.safetensors CLIP loader input — not a video-captioning base for finetune-vlm/--caption-model auto. It is a completely separate artifact from this project's own existing production Qwen3.5-9B base repo, produced for a different consumer (Krea2's own ComfyUI workflow, not this project's own caption-training pipeline) and published to its own, independent HF Hub repo.
merge export strategy).fp8/: the same checkpoint, cast to torch.float8_e4m3fn per-tensor for smaller VRAM footprint. This is a straightforward cast, not Krea2's own fp8_scaled format (a calibrated per-tensor scale factor computed to preserve dynamic range better than a naive cast) — disclosed honestly, not claimed as exact parity with the official qwen3vl_4b_fp8_scaled.safetensors checkpoint. A calibrated scaled-fp8 conversion, if needed, is a separate, later concern (this project's qwen3vl-encoder-abliteration epic).Apache 2.0, inherited from the base model (Qwen/Qwen3-VL-4B-Instruct). Abliteration only edits existing weights (no new copyrighted material introduced), so the original license carries through.