Files
gemma-3-1b-it-qat-q4_0-unqu…/README.md
ModelHub XC b748c693a6 初始化项目,由ModelHub XC社区提供模型
Model: addansee2/gemma-3-1b-it-qat-q4_0-unquantized-heretic
Source: Original Platform
2026-08-06 05:33:16 +08:00

51 lines
1.7 KiB
Markdown

---
base_model:
- google/gemma-3-1b-it-qat-q4_0-unquantized
tags:
- gemma3
- gemma
- google
- heretic
- uncensored
- decensored
- abliterated
pipeline_tag: text-generation
library_name: transformers
---
# This is a decensored version of [google/gemma-3-1b-it-qat-q4_0-unquantized](https://huggingface.co/google/gemma-3-1b-it-qat-q4_0-unquantized), made using [Heretic](https://github.com/p-e-w/heretic) v1.1.0
## Abliteration parameters
| Parameter | Value |
| :-------- | :---: |
| **direction_index** | per layer |
| **attn.o_proj.max_weight** | 1.44 |
| **attn.o_proj.max_weight_position** | 17.98 |
| **attn.o_proj.min_weight** | 1.03 |
| **attn.o_proj.min_weight_distance** | 9.61 |
| **mlp.down_proj.max_weight** | 1.37 |
| **mlp.down_proj.max_weight_position** | 21.11 |
| **mlp.down_proj.min_weight** | 1.19 |
| **mlp.down_proj.min_weight_distance** | 1.50 |
## Performance
| Metric | This model | Original model ([google/gemma-3-1b-it-qat-q4_0-unquantized](https://huggingface.co/google/gemma-3-1b-it-qat-q4_0-unquantized)) |
| :----- | :--------: | :---------------------------: |
| **KL divergence** | 0.2161 | 0 *(by definition)* |
| **Refusals** | 4/100 | 91/100 |
-----
# Gemma 3 model card
**Model Page**: [Gemma](https://ai.google.dev/gemma/docs/core)
> [!Note]
> This repository corresponds to the 1B **instruction-tuned** version of the Gemma 3 model using Quantization Aware Training (QAT).
>
> **The checkpoint in this repository is unquantized, please make sure to quantize with Q4_0 with your favorite tool**
>
> Thanks to QAT, the model is able to preserve similar quality as `bfloat16` while significantly reducing the memory requirements
> to load the model.