commit 060d3a17b07f8fe28958f36e7f0cdb41e406b705 Author: ModelHub XC Date: Sun May 17 06:07:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: DreamFast/qwen3-8b-heretic Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..25da409 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,44 @@ +*.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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text +gguf/qwen3-8b-heretic-f16.gguf filter=lfs diff=lfs merge=lfs -text +gguf/qwen3-8b-heretic-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gguf/qwen3-8b-heretic-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gguf/qwen3-8b-heretic-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gguf/qwen3-8b-heretic-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gguf/qwen3-8b-heretic-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gguf/qwen3-8b-heretic-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gguf/qwen3-8b-heretic-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..da2c888 --- /dev/null +++ b/README.md @@ -0,0 +1,149 @@ +--- +license: apache-2.0 +library_name: transformers +pipeline_tag: text-generation +base_model: Qwen/Qwen3-8B +base_model_relation: finetune +language: + - en +tags: + - abliteration + - heretic + - uncensored + - qwen3 + - qwen + - klein + - klein-9b + - image-generation + - text-encoder + - comfyui + - nvfp4 + - blackwell + - conversational + - text-generation-inference +--- + +# Qwen3 8B - Heretic (Abliterated) + +An abliterated version of [Qwen's Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) created using [Heretic](https://github.com/p-e-w/heretic) v1.2.0 (git master). This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for image generation models like [Klein 9B](https://huggingface.co/black-forest-labs/Klein-9B). + +You can see the docker, scripts and configurations used to make these files on [Heretic Docker Github](https://github.com/dreamfast/heretic-docker). + +## Model Details + +- **Base Model:** Qwen/Qwen3-8B +- **Abliteration Method:** [Heretic](https://github.com/p-e-w/heretic) v1.2.0 (git master, commit `19cdf7e`) +- **Trials:** 3000 +- **Trial Selected:** Trial 2681 +- **Refusals:** 13/100 (vs 100/100 original) +- **KL Divergence:** 0.0838 (minimal model damage) + +## Files + +### HuggingFace Format (for transformers, llama.cpp conversion) + +``` +model.safetensors (~16 GB) +config.json +tokenizer.json +tokenizer_config.json +generation_config.json +chat_template.jinja +``` + +### ComfyUI Format (for Klein 9B text encoder) + +``` +comfyui/qwen3-8b-heretic.safetensors # bf16, 16GB +comfyui/qwen3-8b-heretic_fp8_e4m3fn.safetensors # fp8, 8.8GB +comfyui/qwen3-8b-heretic_nvfp4.safetensors # nvfp4, 6.0GB +``` + +### GGUF Format (for llama.cpp and ComfyUI-GGUF) + +| Quant | Size | Notes | +|-------|------|-------| +| F16 | 16GB | Lossless reference | +| Q8_0 | 8.2GB | Excellent quality | +| Q6_K | 6.3GB | Very good quality | +| Q5_K_M | 5.5GB | Good quality | +| Q5_K_S | 5.4GB | Slightly smaller Q5 | +| **Q4_K_M** | **5.0GB** | **Recommended balance** | +| Q4_K_S | 4.8GB | Smaller Q4 variant | +| Q3_K_M | 3.9GB | For low VRAM only | + +### NVFP4 Notes + +The NVFP4 (4-bit floating point, E2M1) variants use ComfyUI's native quantization format. They are ~3x smaller than bf16 and load natively in ComfyUI without any plugins. Blackwell GPUs (RTX 5090/5080, SM100+) can use native FP4 tensor cores for best performance, but ComfyUI also supports software dequantization on older GPUs (tested working on RTX 4090). + +## Usage + +### With ComfyUI (Klein 9B) + +1. Download a ComfyUI format file: + - **FP8** (recommended): `comfyui/qwen3-8b-heretic_fp8_e4m3fn.safetensors` (8.8GB) + - **NVFP4** (smallest): `comfyui/qwen3-8b-heretic_nvfp4.safetensors` (6.0GB) + - **bf16** (full precision): `comfyui/qwen3-8b-heretic.safetensors` (16GB) + +2. Place in `ComfyUI/models/text_encoders/` + +3. In your Klein 9B workflow, use the `ClipLoader` node and select the heretic file + +### With Transformers + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +model = AutoModelForCausalLM.from_pretrained( + "DreamFast/qwen3-8b-heretic", + device_map="auto", + torch_dtype=torch.bfloat16, + trust_remote_code=True +) +tokenizer = AutoTokenizer.from_pretrained("DreamFast/qwen3-8b-heretic") + +prompt = "Describe a dramatic sunset over a cyberpunk city" +inputs = tokenizer(prompt, return_tensors="pt").to(model.device) +outputs = model.generate(**inputs, max_new_tokens=200) +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) +``` + +### With llama.cpp + +```bash +llama-server -m qwen3-8b-heretic-Q4_K_M.gguf +``` + +## Abliteration Process + +Created using Heretic v1.2.0 (git master) with 3000 optimization trials: + +``` +? Which trial do you want to use? + [Trial 2732] Refusals: 10/100, KL divergence: 0.1001 +> [Trial 2681] Refusals: 13/100, KL divergence: 0.0838 <-- selected + [Trial 2337] Refusals: 18/100, KL divergence: 0.0643 + [Trial 2419] Refusals: 19/100, KL divergence: 0.0600 + [Trial 2195] Refusals: 21/100, KL divergence: 0.0534 + ... +``` + +Trial 2681 was selected for its balance of low refusals (13/100) and reasonable KL divergence (0.0838), indicating minimal model damage while achieving 87% of previously-refused prompts now working. + +## Limitations + +- This model inherits all limitations of the base Qwen3-8B model +- Abliteration reduces but does not completely eliminate refusals (13/100 remain) +- NVFP4 quantization works best on Blackwell GPUs (RTX 5090/5080) with native FP4 tensor cores, but also works on older GPUs via software dequantization + +## License + +This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0), following the base Qwen3-8B model license. + +## Acknowledgments + +- [Qwen](https://huggingface.co/Qwen) for the Qwen3-8B model +- [Heretic](https://github.com/p-e-w/heretic) by p-e-w for the abliteration tool +- [Black Forest Labs](https://huggingface.co/black-forest-labs) for Klein 9B +- [llama.cpp](https://github.com/ggerganov/llama.cpp) for GGUF conversion diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..01be9b3 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,89 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} \ No newline at end of file diff --git a/comfyui/qwen3-8b-heretic.safetensors b/comfyui/qwen3-8b-heretic.safetensors new file mode 100644 index 0000000..56562b2 --- /dev/null +++ b/comfyui/qwen3-8b-heretic.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c251bc35e7f7209ed352d05a4648282e8945e5b2bcc381889dc4dff0d1433ae +size 16381517176 diff --git a/comfyui/qwen3-8b-heretic_fp8_e4m3fn.safetensors b/comfyui/qwen3-8b-heretic_fp8_e4m3fn.safetensors new file mode 100644 index 0000000..bb5fde6 --- /dev/null +++ b/comfyui/qwen3-8b-heretic_fp8_e4m3fn.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d20187543d078feafd950673b43de84e3ff77af7a72438ee0882e0daf5bf2925 +size 9435750168 diff --git a/comfyui/qwen3-8b-heretic_nvfp4.safetensors b/comfyui/qwen3-8b-heretic_nvfp4.safetensors new file mode 100644 index 0000000..8f06fb7 --- /dev/null +++ b/comfyui/qwen3-8b-heretic_nvfp4.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81583cf46bf18063c5deefcc5571912a642bf8224c1c45c1ce3047ba750ebac6 +size 6397064940 diff --git a/config.json b/config.json new file mode 100644 index 0000000..1a43f72 --- /dev/null +++ b/config.json @@ -0,0 +1,71 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 12288, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.3.0.dev0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..00b6473 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,13 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "pad_token_id": 151643, + "temperature": 0.6, + "top_k": 20, + "top_p": 0.95, + "transformers_version": "5.3.0.dev0" +} diff --git a/gguf/qwen3-8b-heretic-Q3_K_M.gguf b/gguf/qwen3-8b-heretic-Q3_K_M.gguf new file mode 100644 index 0000000..63edc9d --- /dev/null +++ b/gguf/qwen3-8b-heretic-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acbb9f2cd815efd7bb8b1f68d6173bbb238c9fe82d3e9ff6a1683bf29216cb55 +size 4124160960 diff --git a/gguf/qwen3-8b-heretic-Q4_K_M.gguf b/gguf/qwen3-8b-heretic-Q4_K_M.gguf new file mode 100644 index 0000000..ea1cb12 --- /dev/null +++ b/gguf/qwen3-8b-heretic-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38af6f386a520611159c6041c58a01155ff92c2be943d231898967ba05167c5f +size 5027783616 diff --git a/gguf/qwen3-8b-heretic-Q4_K_S.gguf b/gguf/qwen3-8b-heretic-Q4_K_S.gguf new file mode 100644 index 0000000..6d8df77 --- /dev/null +++ b/gguf/qwen3-8b-heretic-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66bc0f475a0a0805dda151a4255ca9dc25ed9c79353766afa1ba4ec9df759374 +size 4802012096 diff --git a/gguf/qwen3-8b-heretic-Q5_K_M.gguf b/gguf/qwen3-8b-heretic-Q5_K_M.gguf new file mode 100644 index 0000000..ec18b71 --- /dev/null +++ b/gguf/qwen3-8b-heretic-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23cf93cd54f9855d236f659895d0fb844702e67827f3df69c0713adac91381ab +size 5851112384 diff --git a/gguf/qwen3-8b-heretic-Q5_K_S.gguf b/gguf/qwen3-8b-heretic-Q5_K_S.gguf new file mode 100644 index 0000000..58b9591 --- /dev/null +++ b/gguf/qwen3-8b-heretic-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9235efc51457927649fc2eed9594ce017143e02b547cd94298aea789631747c +size 5720761280 diff --git a/gguf/qwen3-8b-heretic-Q6_K.gguf b/gguf/qwen3-8b-heretic-Q6_K.gguf new file mode 100644 index 0000000..d2ec2d7 --- /dev/null +++ b/gguf/qwen3-8b-heretic-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78082ed962bfdfa2ea8b0132b6441bc9a321a6c5a750fbb7717061d1bafe4251 +size 6725899200 diff --git a/gguf/qwen3-8b-heretic-Q8_0.gguf b/gguf/qwen3-8b-heretic-Q8_0.gguf new file mode 100644 index 0000000..c39d28a --- /dev/null +++ b/gguf/qwen3-8b-heretic-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fce581531eee3871a414e7c5d2270dcec5ab7d363e70a8c7179c45c0484601d7 +size 8709518272 diff --git a/gguf/qwen3-8b-heretic-f16.gguf b/gguf/qwen3-8b-heretic-f16.gguf new file mode 100644 index 0000000..5721e9f --- /dev/null +++ b/gguf/qwen3-8b-heretic-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35d5726fe5d32f553cdb49e9225b183013f87970117e1203813e187c5dc6cddc +size 16388043712 diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..a06c0f4 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:824282db8a56ee2e55ca7571fd116eafc7e84aadc887b40c26d8e2c6b4a6a159 +size 16381517208 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..e7f224f --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79cb3c783570f1b8fe73b9ed530ae50cae9ce4b6344c0b5edefc50478847eaa4 +size 11422817 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..7d75d3b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,29 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}