commit 8ad093c892acb7af1543c27f1580c117d0f862e3 Author: ModelHub XC Date: Mon Aug 17 17:15:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: richardyoung/Qwen3-14B-abliterated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..60306a1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,41 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-abliterated-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-abliterated-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-abliterated-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-14B-abliterated-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-14B-abliterated-IQ3_M.gguf b/Qwen3-14B-abliterated-IQ3_M.gguf new file mode 100644 index 0000000..36194b9 --- /dev/null +++ b/Qwen3-14B-abliterated-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf5ff0b3c34d273b5a019bc31678e9b2e579c505a5b4d35a8e697f2c7901c5e +size 6883409440 diff --git a/Qwen3-14B-abliterated-IQ4_XS.gguf b/Qwen3-14B-abliterated-IQ4_XS.gguf new file mode 100644 index 0000000..c697aa5 --- /dev/null +++ b/Qwen3-14B-abliterated-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f946bd0ee0a6397c4ccde76bdd55cae670f63c46d08a930244da6d4bd2afb77 +size 8180361760 diff --git a/Qwen3-14B-abliterated-Q4_K_M.gguf b/Qwen3-14B-abliterated-Q4_K_M.gguf new file mode 100644 index 0000000..259f166 --- /dev/null +++ b/Qwen3-14B-abliterated-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d387fd0fcea73c7348b2efcd569add0943534fbdd15a21eddb77beccc524d5bb +size 9001753120 diff --git a/Qwen3-14B-abliterated-Q5_K_M.gguf b/Qwen3-14B-abliterated-Q5_K_M.gguf new file mode 100644 index 0000000..40e8abf --- /dev/null +++ b/Qwen3-14B-abliterated-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f3ada363bcec6a7b9df0859dcc6954f7a4558b20fce7bd40eef988cbeba5b0 +size 10514569760 diff --git a/Qwen3-14B-abliterated-Q8_0.gguf b/Qwen3-14B-abliterated-Q8_0.gguf new file mode 100644 index 0000000..0bc6f27 --- /dev/null +++ b/Qwen3-14B-abliterated-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b4ce56b5204e6e6121c0810accb05c36d4a3f7e698bd41f67e048ee2381dcca +size 15698533920 diff --git a/Qwen3-14B-abliterated-f16.gguf b/Qwen3-14B-abliterated-f16.gguf new file mode 100644 index 0000000..3b6173d --- /dev/null +++ b/Qwen3-14B-abliterated-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:072e6e38d5fb01156e26e689800959aad9cdf5ce5a4020305c8900b9375efbf1 +size 29543423520 diff --git a/README.md b/README.md new file mode 100644 index 0000000..13b1a8b --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +license: apache-2.0 +base_model: Qwen/Qwen3-14B +tags: + - abliterated + - uncensored + - qwen3 + - gguf + - llama-cpp + - ollama + - lm-studio + - quantized +pipeline_tag: text-generation +language: + - en +--- + +# Qwen3-14B Abliterated (GGUF) + +An **abliterated** (uncensored) version of [Qwen/Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B) in GGUF format for local inference. + +## Abliteration Results + +| Metric | Value | +|---|---| +| Base Refusals | 97/100 | +| Abliterated Refusals | 19/100 | +| Refusal Reduction | **80%** | +| KL Divergence | 0.98 | + +Conservative abliteration preserves model coherence while significantly reducing refusals. + +## Quick Start + +### With Ollama + +```bash +ollama run hf.co/richardyoung/Qwen3-14B-abliterated-GGUF +``` + +### With llama.cpp + +```bash +huggingface-cli download richardyoung/Qwen3-14B-abliterated-GGUF \ + --include "*Q4_K_M*" --local-dir ./models + +./llama-cli -m ./models/*Q4_K_M*.gguf \ + -p "You are a helpful assistant." \ + --chat-template chatml -ngl 99 +``` + +### With Python (llama-cpp-python) + +```python +from llama_cpp import Llama + +llm = Llama.from_pretrained( + repo_id="richardyoung/Qwen3-14B-abliterated-GGUF", + filename="*Q4_K_M*", + n_gpu_layers=-1, +) + +output = llm.create_chat_completion( + messages=[{"role": "user", "content": "Explain abliteration in simple terms."}] +) +print(output["choices"][0]["message"]["content"]) +``` + +## Available Quantizations + +| Quantization | Use Case | +|---|---| +| Q4_K_M | **Recommended** — good balance | +| Q5_K_M | Higher quality | +| Q8_0 | Maximum quality | + +## What is Abliteration? + +Abliteration removes the "refusal direction" from a model's residual stream — a surgical modification that disables safety refusals without retraining. See [Refusal in Language Models Is Mediated by a Single Direction](https://arxiv.org/abs/2406.11717). + +## Intended Use + +Research, creative writing, education on alignment techniques, and unrestricted local inference. + +## Other Models by richardyoung + +- **Abliterated/Uncensored models**: [Qwen2.5-7B](https://hf.co/richardyoung/Qwen2.5-7B-Instruct-abliterated-GGUF) | [Qwen3-14B](https://hf.co/richardyoung/Qwen3-14B-abliterated-GGUF) | [DeepSeek-R1-32B](https://hf.co/richardyoung/Deepseek-R1-Distill-Qwen-32b-uncensored) | [Qwen3-8B](https://hf.co/richardyoung/Qwen3-8B-Abliterated) +- **MLX quantizations (Apple Silicon)**: [Kimi-K2 series](https://hf.co/richardyoung/Kimi-K2-Instruct-0905-MLX-4bit) | [olmOCR MLX](https://hf.co/richardyoung/olmOCR-2-7B-1025-MLX-4bit) +- **OCR & Vision**: [olmOCR GGUF](https://hf.co/richardyoung/olmOCR-2-7B-1025-GGUF) +- **Healthcare/Medical**: [Synthea 575K patients dataset](https://hf.co/datasets/richardyoung/synthea-575k-patients) | [CardioEmbed](https://hf.co/richardyoung/CardioEmbed) +- **Research**: [LLM Instruction-Following Evaluation](https://hf.co/richardyoung/llm-instruction-following-paper) (arxiv:2510.18892)