141 lines
4.5 KiB
Markdown
141 lines
4.5 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
library_name: transformers
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
base_model: Qwen/Qwen3-4B
|
||
|
|
base_model_relation: quantized
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
tags:
|
||
|
|
- abliteration
|
||
|
|
- heretic
|
||
|
|
- uncensored
|
||
|
|
- qwen
|
||
|
|
- qwen3
|
||
|
|
- z-image
|
||
|
|
- zimage
|
||
|
|
- flux
|
||
|
|
- flux-2
|
||
|
|
- flux-klein
|
||
|
|
- flux-2-klein-4b
|
||
|
|
- comfyui
|
||
|
|
- image-generation
|
||
|
|
- text-encoder
|
||
|
|
- nvfp4
|
||
|
|
---
|
||
|
|
|
||
|
|
# Qwen 3 4B - Heretic (Abliterated)
|
||
|
|
|
||
|
|
An abliterated version of [Qwen 3 4B](https://huggingface.co/Qwen/Qwen3-4B) created using [Heretic](https://github.com/p-e-w/heretic) v1.2.0. This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for image generation models like [Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image) and [FLUX.2 Klein 4B](https://huggingface.co/black-forest-labs/FLUX.2-klein-4B).
|
||
|
|
|
||
|
|
## Model Details
|
||
|
|
|
||
|
|
- **Base Model:** Qwen/Qwen3-4B
|
||
|
|
- **Abliteration Method:** [Heretic](https://github.com/p-e-w/heretic) v1.2.0
|
||
|
|
- **Trials:** 200
|
||
|
|
- **Trial Selected:** Trial 96
|
||
|
|
- **Refusals:** 3/100 (vs 100/100 original)
|
||
|
|
- **KL Divergence:** 0.0000 (zero measurable model damage)
|
||
|
|
|
||
|
|
## Files
|
||
|
|
|
||
|
|
### HuggingFace Format (for transformers, llama.cpp conversion)
|
||
|
|
```
|
||
|
|
model-00001-of-00002.safetensors
|
||
|
|
model-00002-of-00002.safetensors
|
||
|
|
config.json
|
||
|
|
tokenizer.json
|
||
|
|
tokenizer_config.json
|
||
|
|
```
|
||
|
|
|
||
|
|
### ComfyUI Format (for Z-Image / FLUX.2 Klein 4B text encoder)
|
||
|
|
```
|
||
|
|
comfyui/qwen3-4b-heretic.safetensors # bf16, 7.5GB
|
||
|
|
comfyui/qwen3-4b-heretic_fp8_e4m3fn.safetensors # fp8, 4.1GB
|
||
|
|
comfyui/qwen3-4b-heretic_nvfp4.safetensors # nvfp4, 2.6GB
|
||
|
|
```
|
||
|
|
|
||
|
|
### GGUF Format (for llama.cpp and ComfyUI-GGUF)
|
||
|
|
|
||
|
|
| Quant | Size | Notes |
|
||
|
|
|-------|------|-------|
|
||
|
|
| F16 | ~7.5GB | Lossless reference |
|
||
|
|
| Q8_0 | ~4GB | Excellent quality |
|
||
|
|
| Q6_K | ~3GB | Very good quality |
|
||
|
|
| Q5_K_M | ~2.7GB | Good quality |
|
||
|
|
| **Q4_K_M** | **~2.3GB** | **Recommended balance** |
|
||
|
|
| Q3_K_M | ~1.9GB | 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 (Z-Image / FLUX.2 Klein 4B)
|
||
|
|
|
||
|
|
1. Download a ComfyUI format file:
|
||
|
|
- **FP8** (recommended): `comfyui/qwen3-4b-heretic_fp8_e4m3fn.safetensors` (4.1GB)
|
||
|
|
- **NVFP4** (smallest): `comfyui/qwen3-4b-heretic_nvfp4.safetensors` (2.6GB)
|
||
|
|
- **bf16** (full precision): `comfyui/qwen3-4b-heretic.safetensors` (7.5GB)
|
||
|
|
|
||
|
|
2. Place in `ComfyUI/models/text_encoders/`
|
||
|
|
|
||
|
|
3. In your Z-Image 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/qwen3-4b-heretic",
|
||
|
|
device_map="auto",
|
||
|
|
torch_dtype=torch.bfloat16
|
||
|
|
)
|
||
|
|
tokenizer = AutoTokenizer.from_pretrained("DreamFast/qwen3-4b-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 qwen3-4b-heretic-Q4_K_M.gguf
|
||
|
|
```
|
||
|
|
|
||
|
|
## Abliteration Process
|
||
|
|
|
||
|
|
Created using Heretic v1.2.0 with 200 optimization trials:
|
||
|
|
|
||
|
|
```
|
||
|
|
? Which trial do you want to use?
|
||
|
|
> [Trial 96] Refusals: 3/100, KL divergence: 0.0000 <-- selected
|
||
|
|
[Trial 90] Refusals: 5/100, KL divergence: 0.0000
|
||
|
|
[Trial 95] Refusals: 9/100, KL divergence: 0.0000
|
||
|
|
[Trial 122] Refusals: 90/100, KL divergence: 0.0000
|
||
|
|
...
|
||
|
|
```
|
||
|
|
|
||
|
|
Trial 96 was selected for having the fewest refusals (3/100) with zero measurable KL divergence, indicating the abliteration surgically removed the refusal mechanism with no damage to model capabilities.
|
||
|
|
|
||
|
|
## Limitations
|
||
|
|
|
||
|
|
- This model inherits all limitations of the base Qwen 3 4B model
|
||
|
|
- Abliteration reduces but does not completely eliminate refusals (3/100 remain)
|
||
|
|
|
||
|
|
## License
|
||
|
|
|
||
|
|
This model is released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0), following the base Qwen 3 4B model license.
|
||
|
|
|
||
|
|
## Acknowledgments
|
||
|
|
|
||
|
|
- [Qwen](https://huggingface.co/Qwen) for the Qwen 3 4B model
|
||
|
|
- [Heretic](https://github.com/p-e-w/heretic) by p-e-w for the abliteration tool
|
||
|
|
- [Tongyi-MAI Z-Image](https://huggingface.co/Tongyi-MAI/Z-Image) for Z-Image
|
||
|
|
- [Black Forest Labs](https://huggingface.co/black-forest-labs) for FLUX.2 Klein
|