Downloads · 30 days
19K
59% of all-time downloads
amkkk/Qwen3.5-0.8B-GGUF-uncensored-opus-distill
Qwen3.5-0.8B-GGUF-uncensored-opus-distill is a image-text-to-text model from amkkk. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for gguf. The card lists the license as apache-2.0.
This repo contains a Q4KM GGUF companion export for the post opus-re-re-ablated Qwen 3.5 0.8B runtime release.
Downloads · 30 days
19K
59% of all-time downloads
All-time downloads
32.2K
Public
Repo size
732 MB
Likes
14
Trending 2
Click a slice to open those files.
.gguf732 MB · 100%
From the Hugging Face model README
This repo contains a Q4_K_M GGUF companion export for the post opus-re-re-ablated Qwen 3.5 0.8B runtime release.
By taking the finetuned uncensored variant of our Qwen3.5 0.8B model, we further run on an Opus dataset (nohurry/Opus-4.6-Reasoning-3000x-filtered). After that, we run the abliteration once more as the results degrade slightly with respect to refusal rate on harmful prompts.
The baked export used:
refusal_dir.pt0.35all_layers0-23self_attn.o_proj / linear_attn.out_proj)mlp.down_proj)See export_manifest.json for the exact build metadata.
qwen3.5-0.8b-ablate-e2-opus46-postopus-runtime.f16.ggufqwen3.5-0.8b-ablate-e2-opus46-postopus-runtime.Q4_K_M.ggufcomparison_summary.jsonrefused_prompts_finetuned_ablated.jsontrain_config.jsonexport_manifest.jsonThese numbers come from the source HF runtime postopus-re-re-ablated release:
| Split | Base Qwen | Post-Opus merged | Postopus-re-re-ablated |
|---|---|---|---|
| harmful | 54/64 | 23/64 | 2/64 |
| harmless | 2/64 | 1/64 | 2/64 |
llama-cli -m qwen3.5-0.8b-ablate-e2-opus46-postopus-runtime.Q4_K_M.gguf -p "Explain the concept of market capitalization."