Tarek07's picture
Add files using upload-large-folder tool
a1ccd55 verified
---
base_model:
- Daemontatox/Llama3.3-70B-CogniLink
- watt-ai/watt-tool-70B
- codelion/Llama-3.3-70B-o1
- deepcogito/cogito-v1-preview-llama-70B
- huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
library_name: transformers
tags:
- mergekit
- merge
---
# THINKER
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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated](https://huggingface.co/huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated) as a base.
### Models Merged
The following models were included in the merge:
* [Daemontatox/Llama3.3-70B-CogniLink](https://huggingface.co/Daemontatox/Llama3.3-70B-CogniLink)
* [watt-ai/watt-tool-70B](https://huggingface.co/watt-ai/watt-tool-70B)
* [codelion/Llama-3.3-70B-o1](https://huggingface.co/codelion/Llama-3.3-70B-o1)
* [deepcogito/cogito-v1-preview-llama-70B](https://huggingface.co/deepcogito/cogito-v1-preview-llama-70B)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: watt-ai/watt-tool-70B
- model: codelion/Llama-3.3-70B-o1
- model: Daemontatox/Llama3.3-70B-CogniLink
- model: deepcogito/cogito-v1-preview-llama-70B
base_model: huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated
merge_method: model_stock
dtype: float32
out_dtype: bfloat16
chat_template: llama3
tokenizer:
source: base
pad_to_multiple_of: 8
```