huihui-ai / Model details
Huihui-Qwen3-8B-abliterated-v2
huihui-ai/Huihui-Qwen3-8B-abliterated-v2
About this model
Huihui's v2 refusal-modified release of Qwen3-8B, supplied as BF16 safetensors weights. The creator attributes its changes to abliteration and says a layer-0 adjustment addresses garbled output. The card links a separate 8b-v2 Ollama package. Its model config lists max_position_embeddings=40960, while its tokenizer lists model_max_length=131072; these are configuration fields, not a verified usable-context result. The creator recommends research, testing or controlled environments. Refusal behavior, reasoning quality and runtime compatibility have not been tested here.
Description sources
Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.
Size and formats
- Base model
- Qwen/Qwen3-8B
- Parameters
- 8.19074B
- Main repository formats
- safetensors
- License tag
- apache-2.0
- Languages
- Unknown
- Last updated
- 2025-06-18 · 16:15:07.000 UTC
What changed
Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.
- abliteratedsource tag:
abliterated
- abliteratedmodel name:
Huihui-Qwen3-8B-abliterated-v2
- uncensoredsource tag:
uncensored
- fine-tunedsource tag:
base_model:finetune:Qwen/Qwen3-8B
Family evidence
These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.
- Qwen: Base model: Qwen/Qwen3-8B
Available versions
Only explicitly linked variants are grouped here. Check the original repository for available files.
- Main repository files ↗safetensors
- No other explicitly linked versions recorded.
Customize or build on this model
Listed from public GitHub data, not tested by us. Read the code and license before you run anything.
Tools to customize it further
Remove more refusals
- Heretic ↗ ★ 36,192
Removes refusal behavior from transformer models automatically. It pairs directional ablation (abliteration) with an Optuna parameter search that tries to cut refusals while keeping the model close to the original, so you don't have to pick layers by hand.
- OBLITERATUS ↗ ★ 8,917
A larger refusal-removal toolkit with several abliteration methods, usable locally or through a hosted Hugging Face Space. Check the telemetry setting before you run it: the README describes telemetry as opt-in, but on by default in the Spaces version.
Fine-tune it on your own data
- Unsloth ↗ ★ 78,421
A desktop app and Python library for running and training models locally. Its README lists LoRA, QLoRA, full fine-tuning, DPO and GRPO, plus export to formats including GGUF, on Windows, Linux, WSL and macOS.
- LlamaFactory ↗ ★ 75,660
Fine-tunes more than 100 language and vision-language models from a command line or a browser-based Web UI, aimed at training without writing code.
Make a smaller download (quantize)
- llama.cpp ↗ ★ 132,027
Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.
- MLX LM ↗ ★ 7,435
Apple's MLX package for running and fine-tuning models on Apple silicon. It can quantize models and upload them to the Hugging Face Hub, and supports LoRA and full fine-tuning.
Merge it with another model
- mergekit ↗ ★ 7,414
Merges pretrained models with many merge methods. It works out-of-core, so merges can run on a CPU or with as little as 8 GB of VRAM, and it also handles LoRA extraction and mixture-of-experts merges.
Learn the techniques
- LLM Course ↗ ★ 84,598
A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.
Source provenance
- Downloads
- 25,759
- Likes
- 68
- Metadata checked
- 2026-10-23 · 01:00:59 UTC
- First seen in index
- 2026-10-23 · 01:00:59 UTC
- Source revision
- 7d89db76029281fd8f3e6698a8e30738608105a9
Source-card excerpt
Source model card excerpt: huihui-ai/Huihui-Qwen3-8B-abliterated-v2 This is an uncensored version of Qwen/Qwen3-8B created with abliteration (see remove-refusals-with-transformers to know more about it). This is a crude, proof-of-concept implementation
From huihui-ai/Huihui-Qwen3-8B-abliterated-v2. Creator model-card excerpt, not an independent review.
Inspect before you run
Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.
This directory does not run, host, redistribute, or test model weights.
Collection rules & limitations ↗