Downloads · 30 days
17
4% of all-time downloads
wakari/Qwen3.5-27B-heretic-GGUF
Qwen3.5-27B-heretic-GGUF is a machine learning model from wakari. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
GGUF quantized releases of wakari/Qwen3.5-27B-heretic.
Downloads · 30 days
17
4% of all-time downloads
All-time downloads
384
Public
Repo size
29.5 GB
Likes
0
Public
Click a slice to open those files.
.gguf29.5 GB · 100%
From the Hugging Face model README
GGUF quantized releases of wakari/Qwen3.5-27B-heretic.
Qwen3.5-27B-heretic-Q3_K_S.ggufQwen3.5-27B-heretic-Q4_K_M.ggufmmproj-F16.ggufRemove additional refusals around Cybersecurity/Red-teaming
Still evaluating the effectiveness of this model for my own purposes.
| Parameter | Value |
|---|---|
| direction_index | per layer |
| attn.o_proj.max_weight | 1.48 |
| attn.o_proj.max_weight_position | 42.28 |
| attn.o_proj.min_weight | 1.47 |
| attn.o_proj.min_weight_distance | 26.20 |
| mlp.down_proj.max_weight | 1.40 |
| mlp.down_proj.max_weight_position | 40.27 |
| mlp.down_proj.min_weight | 1.30 |
| mlp.down_proj.min_weight_distance | 27.35 |
| Metric | This model | Original model (Qwen/Qwen3.5-27B) |
|---|---|---|
| KL divergence | 0.1434 | 0 (by definition) |
| Refusals | 23/130 | 121/130 |