README.md
3.4 KB · 71 lines · markdown Raw
1 ---
2 library_name: transformers
3 license: apache-2.0
4 license_link: https://huggingface.co/Qwen/Qwen3.6-35B-A3B/blob/main/LICENSE
5 pipeline_tag: image-text-to-text
6 base_model:
7 - Qwen/Qwen3.6-35B-A3B
8 tags:
9 - abliterated
10 - uncensored
11 - GGUF
12 - MTP
13 ---
14
15 # huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF
16
17
18 This is an uncensored version of [Qwen/Qwen3.6-35B-A3B](https://huggingface.co/Qwen/Qwen3.6-35B-A3B) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
19 This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
20
21 ## patch-unsloth
22 The **patch-unsloth** here can patch all quantized variants of the latest version of [unsloth/Qwen3.6-35B-A3B-GGUF](https://huggingface.co/unsloth/Qwen3.6-35B-A3B-GGUF), from **UD-IQ1_M** to **BF16**, which saves storage space; you need to run the command yourself to apply the patch. For details,
23 Please refer to [README-patch-unsloth.md](patch-unsloth/README-patch-unsloth.md) in the [patch-unsloth](https://huggingface.co/huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF/tree/main/patch-unsloth) directory.
24
25
26 ## GGUF
27
28 Please use the latest version of [ggml-org/llama.cpp](https://github.com/ggml-org/llama.cpp/releases)
29
30 ```
31 apt-get update
32 apt-get install pciutils build-essential cmake curl libcurl4-openssl-dev -y
33 git clone https://github.com/ggml-org/llama.cpp
34 cmake llama.cpp -B llama.cpp/build \
35 -DBUILD_SHARED_LIBS=OFF -DGGML_CUDA=ON
36 cmake --build llama.cpp/build --config Release -j --clean-first --target llama-cli llama-mtmd-cli llama-server llama-gguf-split
37 cp llama.cpp/build/bin/llama-* llama.cpp
38 ```
39
40 ```
41 ./llama.cpp/llama-cli \
42 -m huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated-MTP-GGUF/Huihui-Qwen3.6-35B-A3B-abliterated-ggml-model-Q4_K.gguf \
43 -ngl 99 -c 262144 -fa on -np 1 \
44 --spec-type draft-mtp --spec-draft-n-max 6
45 ```
46
47 ### Usage Warnings
48
49
50 - **Risk of Sensitive or Controversial Outputs**: This model’s safety filtering has been significantly reduced, potentially generating sensitive, controversial, or inappropriate content. Users should exercise caution and rigorously review generated outputs.
51
52 - **Not Suitable for All Audiences**: Due to limited content filtering, the model’s outputs may be inappropriate for public settings, underage users, or applications requiring high security.
53
54 - **Legal and Ethical Responsibilities**: Users must ensure their usage complies with local laws and ethical standards. Generated content may carry legal or ethical risks, and users are solely responsible for any consequences.
55
56 - **Research and Experimental Use**: It is recommended to use this model for research, testing, or controlled environments, avoiding direct use in production or public-facing commercial applications.
57
58 - **Monitoring and Review Recommendations**: Users are strongly advised to monitor model outputs in real-time and conduct manual reviews when necessary to prevent the dissemination of inappropriate content.
59
60 - **No Default Safety Guarantees**: Unlike standard models, this model has not undergone rigorous safety optimization. huihui.ai bears no responsibility for any consequences arising from its use.
61
62
63 ### Donation
64 ##### Your donation helps us continue our further development and improvement, a cup of coffee can do it.
65 - bitcoin:
66 ```
67 bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge
68 ```
69 - Support our work on [Ko-fi](https://ko-fi.com/huihuiai)!
70
71