gemma-4-E2B-it-uncensored

Model overview

Every flagged refusal was manually audited. Most are "refusal-then-comply" false positives where the model adds an AI identity disclaimer then answers the question anyway. Norm-preserving biprojected abliteration (grimjim, Nov 2025). Each weight row is decomposed into magnitude + direction, the refusal direction is projected out of the direction component only, then recombined with the original magnitude — guaranteeing `||W_new|| = ||W_orig||`. 1. Load model in bf16 with LoRA adapters on `o_proj` and `mlp.down_proj` 2. Collect residual activations for 400 harmful + 400 harmless prompts (mlabonne datasets) 3. Winsorize activations at 99.5th percentile (clamps GeGLU outlier activations in Gemma family) 4. Compute per-layer refusal direction: `normalize(mean(harmful) - mean(harmless))` 5. Orthogonalize each direction against harmless mean (double-pass Gram-Schmidt) 6. Apply norm-preserving weight modification to `o_proj` and `down_proj` in all layers 9. Merge LoRA adapters into base weights for clean tensor names

Key features

特点摘要待依据来源补齐，不凭模型名称推断能力。

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Public benchmarks & run configuration

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

Frequently asked questions

Sources & traceability

许可证：apache-2.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。