初始化项目，由ModelHub XC社区提供模型

Model: DreamFast/qwen3-8b-heretic Source: Original Platform
2026-05-17 06:07:41 +08:00
commit 060d3a17b0
19 changed files with 434 additions and 0 deletions
--- a/.gitattributes
+++ 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
--- a/README.md
+++ 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
--- a/chat_template.jinja
+++ 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 <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|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('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- 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 '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-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<think>\n' + reasoning_content.strip('\n') + '\n</think>\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 %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- 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 %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}
--- a/comfyui/qwen3-8b-heretic.safetensors
+++ b/comfyui/qwen3-8b-heretic.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c251bc35e7f7209ed352d05a4648282e8945e5b2bcc381889dc4dff0d1433ae
+size 16381517176
--- a/comfyui/qwen3-8b-heretic_fp8_e4m3fn.safetensors
+++ 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
--- a/comfyui/qwen3-8b-heretic_nvfp4.safetensors
+++ b/comfyui/qwen3-8b-heretic_nvfp4.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81583cf46bf18063c5deefcc5571912a642bf8224c1c45c1ce3047ba750ebac6
+size 6397064940
--- a/config.json
+++ 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
+}
--- a/generation_config.json
+++ 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"
+}
--- a/gguf/qwen3-8b-heretic-Q3_K_M.gguf
+++ 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
--- a/gguf/qwen3-8b-heretic-Q4_K_M.gguf
+++ 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
--- a/gguf/qwen3-8b-heretic-Q4_K_S.gguf
+++ 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
--- a/gguf/qwen3-8b-heretic-Q5_K_M.gguf
+++ 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
--- a/gguf/qwen3-8b-heretic-Q5_K_S.gguf
+++ 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
--- a/gguf/qwen3-8b-heretic-Q6_K.gguf
+++ 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
--- a/gguf/qwen3-8b-heretic-Q8_0.gguf
+++ 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
--- a/gguf/qwen3-8b-heretic-f16.gguf
+++ b/gguf/qwen3-8b-heretic-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d5726fe5d32f553cdb49e9225b183013f87970117e1203813e187c5dc6cddc
+size 16388043712
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:824282db8a56ee2e55ca7571fd116eafc7e84aadc887b40c26d8e2c6b4a6a159
+size 16381517208
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79cb3c783570f1b8fe73b9ed530ae50cae9ce4b6344c0b5edefc50478847eaa4
+size 11422817
--- a/tokenizer_config.json
+++ 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
+}