---
base_model:
- T3Q-LLM/T3Q-LLM2-FP-v1.0
- hwkwon/S-SOLAR-10.7B-v1.5
- chihoonlee10/T3Q-ko-solar-dpo-v7.0
library_name: transformers
tags:
- mergekit
- merge
license: mit
---
# Untitled Model (1)

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 [T3Q-LLM/T3Q-LLM2-FP-v1.0](https://huggingface.co/T3Q-LLM/T3Q-LLM2-FP-v1.0) as a base.

### Models Merged

The following models were included in the merge:
* [hwkwon/S-SOLAR-10.7B-v1.5](https://huggingface.co/hwkwon/S-SOLAR-10.7B-v1.5)
* [chihoonlee10/T3Q-ko-solar-dpo-v7.0](https://huggingface.co/chihoonlee10/T3Q-ko-solar-dpo-v7.0)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: hwkwon/S-SOLAR-10.7B-v1.5
    parameters:
      density: [1, 0.7, 0.1] # density gradient
      weight: 1.0
  - model: chihoonlee10/T3Q-ko-solar-dpo-v7.0
    parameters:
      density: 0.5
      weight: [0, 0.3, 0.7, 1] # weight gradient
merge_method: dare_ties
base_model: T3Q-LLM/T3Q-LLM2-FP-v1.0
parameters:
  normalize: true
  int8_mask: true
dtype: float16

#mergekit-yaml /path/to/config.yml ./output/directory --cuda 
```