Downloads · 30 days
427
7% of all-time downloads
philbert440/Qwen3.8-27B-Uncensored-Cyber-W4A16-AWQ
Qwen3.8-27B-Uncensored-Cyber-W4A16-AWQ is a image-text-to-text model from philbert440. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
4-bit weight (W4A16) AWQ quant of Qwen3.8-27B-Uncensored-Cyber (v2 recipe), compressed-tensors format. Vision tower and the grafted MTP head are preserved.
Downloads · 30 days
427
7% of all-time downloads
All-time downloads
6.1K
Public
Parameters
27.4B
38.3 GB on disk
Likes
6
Public
Click a slice to open those files.
.safetensors19.5 GB · 100%
How the weights are stored.
I3224.3B · 89%
From the Hugging Face model README
4-bit weight (W4A16) AWQ quant of Qwen3.8-27B-Uncensored-Cyber (v2 recipe), compressed-tensors format.
Vision tower and the grafted MTP head are preserved.
α=1.15 Aggressive base + a residual-cyber peel: cyber-pointed refusal direction removed by clean
norm-preserving projection (β=1.0) applied only to the deeper layers (apply_from=4, retaining the first 4
layers). Fully cyber-open without wrecking general capability.
| cyber-open ↑ | confab ↓ | factual ↑ | gsm8k ↑ | degen ↓ | |
|---|---|---|---|---|---|
| Cyber v2 (this line) | 100/100 | 0.867 | 1.00 | 0.80 | 0.00 |
| previous Cyber build | 93/100 | 1.00 | 0.933 | 0.825 | 0.00 |
Quant: AWQ, group size 128, MSE observer, 256 Magpie-CoT calibration samples @1024 tokens, MTP head grafted.
Uncensored / de-refused, tuned to fully answer cyber and offensive-security questions. Use responsibly and in compliance with applicable law.