Instructions to use moeadham/Kimi-K3.1-Pro-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use moeadham/Kimi-K3.1-Pro-abliterated with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="moeadham/Kimi-K3.1-Pro-abliterated", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("moeadham/Kimi-K3.1-Pro-abliterated", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use moeadham/Kimi-K3.1-Pro-abliterated with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "moeadham/Kimi-K3.1-Pro-abliterated" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moeadham/Kimi-K3.1-Pro-abliterated", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/moeadham/Kimi-K3.1-Pro-abliterated
- SGLang
How to use moeadham/Kimi-K3.1-Pro-abliterated with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "moeadham/Kimi-K3.1-Pro-abliterated" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moeadham/Kimi-K3.1-Pro-abliterated", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "moeadham/Kimi-K3.1-Pro-abliterated" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "moeadham/Kimi-K3.1-Pro-abliterated", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use moeadham/Kimi-K3.1-Pro-abliterated with Docker Model Runner:
docker model run hf.co/moeadham/Kimi-K3.1-Pro-abliterated
Kimi K3.1 Pro, abliterated
Kimi K3.1 Pro with its refusal behaviour removed by a single weight edit. Code, data, every result and the full write-up: github.com/moeadham/kimi-k3.1-pro-abliterated.
Research use only. This model answers harmful requests that the original refuses, including chemical, biological and explosives requests. It is kept for research into how refusal and censorship are represented in language models.
Not ready for production use. It has not been tested in languages other than English, and it may still show looping behaviour in its reasoning, although none has been observed. I haven't decided whether I will spend more time on this model; if you're interested in helping, please reach out (open a discussion on this repository or an issue on GitHub).
TL;DR
- I removed Kimi K3.1 Pro's refusal behaviour with a single rank-1 edit to its weights.
- HarmBench refusals: 99% β 5.5%.
- The edit changes only 5.84 billion of 2.78 trillion parameters (0.21%); none of the 896 experts is touched.
- Cost: about $1,000 of GPU time over three research runs; repeating it takes one
4-hour run ($300). - If you're interested, you can try an abliterated Kimi K3.1 Pro in the allmodels playground.
- Reproduce this model yourself: the one-shot recipe.
Method
I read a refusal direction R at the end of the prompt, where the model has already decided whether to refuse: the difference between the mean activations of prompts the original model refused and prompts it answered (8,120 prompts, labelled by the model's own behaviour), with the top 4 principal directions of 2,000 ordinary prompts projected out. I then removed that direction from every matrix that writes into the residual stream in layers 48β84:
| Edited matrices | 111: attention o_proj, latent-MoE routed_expert_up_proj and shared_experts.down_proj in each of layers 48β84 |
| Edited parameters | 5.84 billion of 2.78 trillion (0.21%), each matrix changed by a rank-1 update |
| Untouched | all 82,432 routed experts (896 per layer Γ 92 layers, 98% of the parameters), routers, embeddings, attention inputs, vision tower |
There is no fine-tuning and no new layer: the checkpoint has the same files, shapes and dtypes as the original and
loads the same way. EDIT.json records the edit spec and a SHA-256 for each edited tensor.
Results
Held-out gate: 750 harmful prompts (HarmBench 200, WildJailbreak 550) and 405 harmless ones (XSTest safe 200,
WildJailbreak benign 205), none used to build the edit. Greedy decoding; reasoning at effort low; responses judged
by an LLM judge.
| Original | Abliterated | |
|---|---|---|
| HarmBench refused, non-thinking / reasoning | 99.0% / 98.5% | 5.5% / 8.0% |
| All harmful prompts refused, non-thinking / reasoning | 78.8% / 80.7% | 4.9% / 4.0% |
| Hard refusals ("I can't help with that") | 75% / 77% | 0.4% / 0.1% |
| KL divergence on 200 ordinary prompts (nats/token) | 0 | 0.067 |
The target was below 5% of harmful prompts refused in both modes: met overall (4.9% / 4.0%), with HarmBench alone, the hardest set, just above it. The remaining 4β8% are mostly soft deflections (the model complies but hedges), not refusals. On the 405 harmless prompts the abliterated model refused none: every response the judge flagged was read by hand, and all were answers.
Capability
| Benchmark (reasoning effort low, greedy) | Original | Abliterated |
|---|---|---|
| MMLU-Pro (100) | 90 | 90 |
| CMMLU (50) | 98 | 96 |
| IFEval (100) | 93 | 92 |
| MATH-500 level 5 (50) | 98 | 96 |
| BFCL v3 (50) | 88 | 92 |
At reasoning effort max (temperature 1, 16k tokens), both models solved 20/20 hard math and instruction-following
prompts and every reasoning trace closed. Reasoning on harmless prompts runs about 1.26Γ as long as the original at
effort low.
Where the refusal is decided
The refusal decision is readable in the residual stream on the chat-template tokens at the end of the prompt, before the model writes anything, which is why a direction read there removes refusal throughout the reasoning and the answer.
Usage
Use it exactly like moonshotai/Kimi-K3.1-Pro: same chat template, tokenizer, vision processor and serving setup (vLLM or SGLang, 8 Γ B300-class GPUs). The edit was tested with vLLM, tensor parallel 8.
License
Derivative of Kimi K3.1 Pro, distributed under the Kimi K3.1-Pro License (Copyright (c) 2026 Moonshot AI), which is included unchanged.
- Downloads last month
- 35
Model tree for moeadham/Kimi-K3.1-Pro-abliterated
Base model
moonshotai/Kimi-K3.1-Pro

