Qwen3.5-4B Heretic MLX
Quality: bfloat16
This is a abliterated (uncensored) version of Qwen/Qwen3.5-4B, made using Heretic v1.2.0 with Multi-directional refusal supression.
This model supports thinking mode, but it is disabled by default.
Abliteration metrics
| Metric | This model | Original model (Qwen/Qwen3.5-4B) |
|---|---|---|
| KL divergence | 0.0406 | 0 (by definition) |
| Refusals | 4/100 | 94/100 |
Sampling Parameters:
- I suggest using the following sets of sampling parameters depending on the mode and task type:
- Thinking mode for general tasks:
temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0 - Thinking mode for precise coding tasks (e.g., WebDev):
temperature=0.6,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=0.0,repetition_penalty=1.0 - Instruct (or non-thinking) mode for general tasks:
temperature=0.7,top_p=0.8,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0 - Instruct (or non-thinking) mode for reasoning tasks:
temperature=1.0,top_p=1.0,top_k=40,min_p=0.0,presence_penalty=2.0,repetition_penalty=1.0
- Thinking mode for general tasks:
- For supported frameworks, you can adjust the
presence_penaltyparameter between 0 and 2 to reduce endless repetitions. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance.
Source
This model was converted to MLX format from coder3101/Qwen3.5-4B-heretic using mlx-vlm version 0.3.12.