Nexesenex's picture
Update README.md
5a89ecc verified
---
base_model:
- huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
- meta-llama/Llama-3.3-70B-Instruct
- meta-llama/Llama-3.1-70B-Instruct
library_name: transformers
tags:
- mergekit
- merge
---
# about
A DL-worthy model, merge of Nemotron Abliterated and Llama 3.3 Instruct, with L3.1 Instruct 70b as a base.
And it's quite smart and verbose, albeit quite a bit prudish.
One of my favorites ATM.
Note : if someone could reproduce the recipe with huihui's Llama 3.3 70b Instruct abliterated (normal version, not the "finetuned") instead of Llama 3.3 70b Instruct, it'd be worth a try.
I don't have access to a mergekit rig atm, now that Arcee's space is down.
---
# 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 [Task Arithmetic](https://arxiv.org/abs/2212.04089) merge method using [meta-llama/Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-70B-Instruct) 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)
* [meta-llama/Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
merge_method: task_arithmetic
base_model: meta-llama/Llama-3.1-70B-Instruct
models:
- model: huihui-ai/Llama-3.1-Nemotron-70B-Instruct-HF-abliterated
parameters:
weight: 1.0
- model: meta-llama/Llama-3.3-70B-Instruct
parameters:
weight: 1.0
dtype: bfloat16 -> replace with float32 if possible
out_dtype: bfloat16
parameters:
int8_mask: true
normalize: false
rescale: false
filter_wise: false
chat_template: auto
tokenizer:
source: union
```