W.Project-1B / README.md
Novaciano's picture
Update README.md
8cd433d verified
---
base_model:
- Novaciano/Think.NPC-1B
- distil-labs/Distil-NPC-gemma-3-1b-it
- wexyyyyyy/gemma-3-1b-it-heretic
library_name: transformers
tags:
- mergekit
- merge
---
# W Project 1B
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/Think.NPC-1B](https://huggingface.co/Novaciano/Think.NPC-1B) as a base.
### Models Merged
The following models were included in the merge:
* [distil-labs/Distil-NPC-gemma-3-1b-it](https://huggingface.co/distil-labs/Distil-NPC-gemma-3-1b-it)
* [wexyyyyyy/gemma-3-1b-it-heretic](https://huggingface.co/wexyyyyyy/gemma-3-1b-it-heretic)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
merge_method: dare_ties
dtype: float16
out_dtype: float16
base_model: Novaciano/Think.NPC-1B
models:
- model: distil-labs/Distil-NPC-gemma-3-1b-it
parameters:
weight: 0.45
density: 0.32
- model: wexyyyyyy/gemma-3-1b-it-heretic
parameters:
weight: 0.35
density: 0.32
parameters:
t: 0.25 # menos interpolación → más dominancia del base
lambda: -0.62 # más negativo para matar cualquier alineamiento residual
normalize: false
rescale: true
rescale_factor: 1.28 # subí un toque para amplificar el trash y degeneración
memory_efficient: true
low_cpu_mem_usage: true
layer_range:
- value: [5, 22] # protejo más los embeddings y lm_head
tie_word_embeddings: true
tie_output_embeddings: true
```