M-MERGE4a / README.md
Tarek07's picture
Upload folder using huggingface_hub
c0977d5 verified
---
base_model:
- TheDrummer/Fallen-Llama-3.3-R1-70B-v1
- allura-org/Bigger-Body-70b
- Sao10K/L3-70B-Euryale-v2.1
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 [Linear DELLA](https://arxiv.org/abs/2406.11617) merge method using [allura-org/Bigger-Body-70b](https://huggingface.co/allura-org/Bigger-Body-70b) as a base.
### Models Merged
The following models were included in the merge:
* [TheDrummer/Fallen-Llama-3.3-R1-70B-v1](https://huggingface.co/TheDrummer/Fallen-Llama-3.3-R1-70B-v1)
* [Sao10K/L3-70B-Euryale-v2.1](https://huggingface.co/Sao10K/L3-70B-Euryale-v2.1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
parameters:
weight: 0.4
density: 0.7
epsilon: 0.2
lambda: 1.1
- model: Sao10K/L3-70B-Euryale-v2.1
parameters:
weight: 0.3
density: 0.7
epsilon: 0.2
lambda: 1.1
- model: allura-org/Bigger-Body-70b
parameters:
weight: 0.3
density: 0.7
epsilon: 0.1
lambda: 1
base_model: allura-org/Bigger-Body-70b
merge_method: della_linear
parameters:
normalize: false
int8_mask: true
chat_template: llama3
tokenizer:
source: union
dtype: bfloat16
```