aashish1904's picture
Upload README.md with huggingface_hub
4f1ec61 verified
|
raw
history blame
2.08 kB
---
base_model:
- ehristoforu/Gemma2-9B-it-psy10k-mental_health
- ehristoforu/Gemma2-9b-it-train6
- princeton-nlp/gemma-2-9b-it-SimPO
- nbeerbower/gemma2-gutenberg-9B
library_name: transformers
tags:
- mergekit
- merge
---
[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)
# QuantFactory/Gemma2-9B-TitanFusion-GGUF
This is quantized version of [bunnycore/Gemma2-9B-TitanFusion](https://huggingface.co/bunnycore/Gemma2-9B-TitanFusion) created using llama.cpp
# Original Model Card
# 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](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [nbeerbower/gemma2-gutenberg-9B](https://huggingface.co/nbeerbower/gemma2-gutenberg-9B) as a base.
### Models Merged
The following models were included in the merge:
* [ehristoforu/Gemma2-9B-it-psy10k-mental_health](https://huggingface.co/ehristoforu/Gemma2-9B-it-psy10k-mental_health)
* [ehristoforu/Gemma2-9b-it-train6](https://huggingface.co/ehristoforu/Gemma2-9b-it-train6)
* [princeton-nlp/gemma-2-9b-it-SimPO](https://huggingface.co/princeton-nlp/gemma-2-9b-it-SimPO)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: princeton-nlp/gemma-2-9b-it-SimPO
parameters:
weight: 0.5
density: 0.5
- model: nbeerbower/gemma2-gutenberg-9B
parameters:
weight: 0.5
density: 0.5
- model: ehristoforu/Gemma2-9B-it-psy10k-mental_health
parameters:
weight: 0.5
density: 0.5
- model: ehristoforu/Gemma2-9b-it-train6
parameters:
weight: 0.5
density: 0.5
merge_method: dare_ties
base_model: nbeerbower/gemma2-gutenberg-9B
dtype: bfloat16
```