---
base_model:
- prithivMLmods/Llama-Chat-Summary-3.2-3B
- prithivMLmods/Llama-Thinker-3B-Preview2
- NousResearch/Hermes-3-Llama-3.2-3B
library_name: transformers
tags:
- mergekit
- merge
license: llama3.2
---
# Merge

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details

Hermes with some CoT and Chat Summary added.

Quant: https://huggingface.co/Triangle104/Hermes-Llama-3.2-CoT-Summary-Q4_K_M-GGUF

### Merge Method

This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [NousResearch/Hermes-3-Llama-3.2-3B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B) as a base.

### Models Merged

The following models were included in the merge:
* [prithivMLmods/Llama-Chat-Summary-3.2-3B](https://huggingface.co/prithivMLmods/Llama-Chat-Summary-3.2-3B)
* [prithivMLmods/Llama-Thinker-3B-Preview2](https://huggingface.co/prithivMLmods/Llama-Thinker-3B-Preview2)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: NousResearch/Hermes-3-Llama-3.2-3B
    #no parameters necessary for base model
  - model: prithivMLmods/Llama-Thinker-3B-Preview2
    parameters:
      density: 0.5
      weight: 0.5
  - model: prithivMLmods/Llama-Chat-Summary-3.2-3B
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: NousResearch/Hermes-3-Llama-3.2-3B
parameters:
  normalize: false
  int8_mask: true
dtype: float16
```