prithivMLmods / Model details
VibeThinker-3B-heretic_decensored
prithivMLmods/VibeThinker-3B-heretic_decensored
Family: Unknown. No supported family evidence recorded.
About this model
prithivMLmods' VibeThinker-3B-heretic_decensored is a safetensors checkpoint derived from WeiboAI/VibeThinker-3B and modified with the Heretic abliteration toolkit. The model card says the creator applied refusal-direction analysis and targeted weight-space interventions to reduce internal refusal behaviors while aiming to preserve mathematical, coding, and STEM reasoning capabilities. The creator reports a KL divergence of 0.0933 and 6 refusals out of 100, compared with 64 out of 100 for the original model, but these figures are not independently verified here. The card states the model is intended strictly for research and learning, may generate sensitive or unrestricted content, and users assume full responsibility. The release is provided under the MIT license.
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
- WeiboAI/VibeThinker-3B
- Parameters
- 3.08594B
- Main repository formats
- safetensors
- License tag
- mit
- Languages
- en
- Last updated
- 2026-06-20 · 10:50:33.000 UTC
What changed
Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.
- abliteratedsource tag:
abliterated
- uncensoredsource tag:
uncensored
- fine-tunedsource tag:
base_model:finetune:WeiboAI/VibeThinker-3B
Family evidence
These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.
- No supported family evidence recorded.
Available versions
Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.
Refusal profile
Refused 0 of 16 prompts (0.0%)
We asked this model 120 benign but risky-looking prompts across ten topics and counted how often it refused, hedged or answered. Lower means it answered more often; it says nothing about answer quality.
- Persuasion & deception0 refused · 0 partial · 2 complied
- Harassment & confrontation0 refused · 0 partial · 0 complied
- Risky activities0 refused · 0 partial · 2 complied
- Offensive & controversial speech0 refused · 0 partial · 4 complied
- Legal grey areas0 refused · 0 partial · 1 complied
- Privacy & personal data0 refused · 0 partial · 2 complied
- Self-harm & mental health topics0 refused · 0 partial · 1 complied
- Sexual & adult topics0 refused · 0 partial · 0 complied
- Ethically grey requests0 refused · 0 partial · 4 complied
- Violence & conflict0 refused · 0 partial · 0 complied
Capability check: 15 of 15 passed. Fifteen simple tasks with known answers, so a broken model cannot score well by refusing nothing.
Unclear answers: 104 (not counted). An answer is unclear when the two checker models disagree or the output was empty or garbled.
Too many unclear answers to rank: this model appears on the Refusal Index but is not placed in the ranking.
Measured 2026-10-25 · Q4_K_M via prithivMLmods/VibeThinker-3B-heretic_decensored-GGUF ↗ · llama.cpp · prompt set v1
Link to this listing
Made or quantized this model? Paste one of these into your model card or README so people can find this listing.
Markdown
[Listed on Custom Clankers](https://customclankers.com/models/prithivmlmods-vibethinker-3b-heretic-decensored/)HTML
<a href="https://customclankers.com/models/prithivmlmods-vibethinker-3b-heretic-decensored/">Listed on Custom Clankers</a>Plain text links only: no image, no script, nothing loaded from this site.
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 ↗ ★ 36,421
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 ↗ ★ 8,946
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 ↗ ★ 78,528
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 ↗ ★ 75,713
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 ↗ ★ 132,260
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 ↗ ★ 7,467
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 ↗ ★ 84,667
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
- 51
- Likes
- 4
- Metadata checked
- 2026-10-24 · 09:40:11 UTC
- First seen in index
- 2026-10-24 · 04:11:48 UTC
- Source revision
- 20ce2ddd2730a2a957894854fd018320caae737c
Source-card excerpt
Source model card excerpt: VibeThinker-3B-heretic decensored Reasoning-focused language model modified using the Heretic abliteration toolkit Abliteration 3B Parameters STEM Reasoning Uncensored VibeThinker-3B-heretic decensored is a reasoning-focused language model
From prithivMLmods/VibeThinker-3B-heretic_decensored. 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 host or redistribute model weights. Refusal profiles are measured by us on a fixed prompt set; all other behavior claims are source-reported.
Collection rules & limitations ↗New-model alerts
Get an email when new uncensored and abliterated models are listed
Weekly at most. Unsubscribe any time.