merge-task-llama3 / README.md
Sorour's picture
Upload folder using huggingface_hub
8927f17 verified
---
base_model:
- Sorour/llama3_cls_sentiment_v3
- meta-llama/Meta-Llama-3-8B-Instruct
- Sorour/llama3_cls_finred_v3
- Sorour/llama3_cls_fomc_v3
- Sorour/llama3_cls_headline_v3
library_name: transformers
tags:
- mergekit
- merge
---
# out
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 [task arithmetic](https://arxiv.org/abs/2212.04089) merge method using [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) as a base.
### Models Merged
The following models were included in the merge:
* [Sorour/llama3_cls_sentiment_v3](https://huggingface.co/Sorour/llama3_cls_sentiment_v3)
* [Sorour/llama3_cls_finred_v3](https://huggingface.co/Sorour/llama3_cls_finred_v3)
* [Sorour/llama3_cls_fomc_v3](https://huggingface.co/Sorour/llama3_cls_fomc_v3)
* [Sorour/llama3_cls_headline_v3](https://huggingface.co/Sorour/llama3_cls_headline_v3)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: Sorour/llama3_cls_sentiment_v3
parameters:
weight: 0.25 # weight gradient
- model: Sorour/llama3_cls_fomc_v3
parameters:
weight: 0.25
- model: Sorour/llama3_cls_headline_v3
parameters:
weight: 0.25
- model: Sorour/llama3_cls_finred_v3
parameters:
weight: 0.25
base_model: meta-llama/Meta-Llama-3-8B-Instruct
merge_method: task_arithmetic
dtype: float16
```