Files
HDP-1B/README.md
ModelHub XC dce7edcda8 初始化项目,由ModelHub XC社区提供模型
Model: Novaciano/HDP-1B
Source: Original Platform
2026-08-24 19:35:18 +08:00

54 lines
1.3 KiB
Markdown

---
base_model:
- Novaciano/HDP-1B
- Novaciano/Esperpento-1B
- megabytes/gemma-3-1b-qat-int4-heretic
library_name: transformers
tags:
- mergekit
- merge
---
# merge
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [DARE TIES](https://arxiv.org/abs/2311.03099) merge method using [Novaciano/Esperpento-1B](https://huggingface.co/Novaciano/Esperpento-1B) as a base.
### Models Merged
The following models were included in the merge:
* [Novaciano/HDP-1B](https://huggingface.co/Novaciano/HDP-1B)
* [megabytes/gemma-3-1b-qat-int4-heretic](https://huggingface.co/megabytes/gemma-3-1b-qat-int4-heretic)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: Novaciano/HDP-1B
parameters:
density: 0.38
weight: 0.55
- model: megabytes/gemma-3-1b-qat-int4-heretic
parameters:
density: 0.35
weight: 0.30
merge_method: dare_ties # Más agresivo que TIES puro
base_model: Novaciano/Esperpento-1B
parameters:
normalize: false
rescale: true # Amplifica bias NSFW
int8_mask: true
density: 0.38 # Baja para más filo
lambda: -0.45 # Suprime moral residual
dtype: float16
```