README.md

---
base_model:
- huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
- hitachi-nlp/Llama-3.1-70B-FLDx2
- TheDrummer/Fallen-Llama-3.3-R1-70B-v1
library_name: transformers
tags:
- mergekit
- merge

---
# abouts

Functionnal merge of Fallen Llama R1 involving Nemotron, and Hitachi FLDx2 instead of Tulu.
Brick for ulterior merge within the SmarTricks series, but works well as a standalone also.
Moderately uncensored.

---
# benchs

PPL Wikitext 512 ENG : 3.19 ; ARC-C : 61.85 ; ARC-E : 82.45.

---
# 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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [TheDrummer/Fallen-Llama-3.3-R1-70B-v1](https://huggingface.co/TheDrummer/Fallen-Llama-3.3-R1-70B-v1) as a base.

### Models Merged

The following models were included in the merge:
* [huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated](https://huggingface.co/huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated)
* [hitachi-nlp/Llama-3.1-70B-FLDx2](https://huggingface.co/hitachi-nlp/Llama-3.1-70B-FLDx2)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
merge_method: model_stock
models:
  - model: hitachi-nlp/Llama-3.1-70B-FLDx2
    parameters:
      weight: 1.0
  - model: huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
    parameters:
      weight: 1.0
base_model: TheDrummer/Fallen-Llama-3.3-R1-70B-v1
dtype: bfloat16
out_dtype: bfloat16
parameters:
  int8_mask: true
  normalize: true
  rescale: false
  filter_wise: false
  smooth: false
  allow_negative_weights: false
chat_template: auto
tokenizer:
  source: union
```