README.md

---
license: llama3.1
library_name: transformers
tags:
- mergekit
- merge
base_model:
- nvidia/Llama-3.1-Nemotron-70B-Instruct-HF
- mlabonne/Llama-3-70B-Instruct-abliterated-LORA
model-index:
- name: Llama-3.1-Nemotron-lorablated-70B
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: IFEval (0-Shot)
      type: HuggingFaceH4/ifeval
      args:
        num_few_shot: 0
    metrics:
    - type: inst_level_strict_acc and prompt_level_strict_acc
      value: 71.47
      name: strict accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: BBH (3-Shot)
      type: BBH
      args:
        num_few_shot: 3
    metrics:
    - type: acc_norm
      value: 48.06
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MATH Lvl 5 (4-Shot)
      type: hendrycks/competition_math
      args:
        num_few_shot: 4
    metrics:
    - type: exact_match
      value: 23.34
      name: exact match
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GPQA (0-shot)
      type: Idavidrein/gpqa
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 0.89
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MuSR (0-shot)
      type: TAUR-Lab/MuSR
      args:
        num_few_shot: 0
    metrics:
    - type: acc_norm
      value: 14.92
      name: acc_norm
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU-PRO (5-shot)
      type: TIGER-Lab/MMLU-Pro
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 43.46
      name: accuracy
    source:
      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=nbeerbower/Llama-3.1-Nemotron-lorablated-70B
      name: Open LLM Leaderboard
---
![image/png](https://huggingface.co/nbeerbower/Llama-3.1-Nemotron-lorablated-70B/resolve/main/nemotron.png?download=true)
# Llama-3.1-Nemotron-lorablated-70B

An uncensored version of [nvidia/Llama-3.1-Nemotron-70B-Instruct-HF](https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF) created by merging [mlabonne/Llama-3-70B-Instruct-abliterated-LORA](https://huggingface.co/mlabonne/Llama-3-70B-Instruct-abliterated-LORA) using [task arithmetic](https://arxiv.org/abs/2212.04089).

## Method

This model was created using [mergekit](https://github.com/cg123/mergekit).

From Ubuntu 24.04 (as root):
```
apt update
apt install pipx
git clone https://github.com/arcee-ai/mergekit.git
cd mergekit && pipx install -e .

mergekit-yaml config.yaml Llama-3.1-Nemotron-lorablated-70B --allow-crimes --lora-merge-cache=./cache
```

See [@mlabonne](https://huggingface.co/mlabonne)'s [Llama-3.1-70B-Instruct-lorablated](https://huggingface.co/mlabonne/Llama-3.1-70B-Instruct-lorablated) for more details on how the LoRA was extracted.

### Configuration

The following YAML configuration was used to produce this model:

```yaml
base_model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF+mlabonne/Llama-3-70B-Instruct-abliterated-LORA
dtype: bfloat16
merge_method: task_arithmetic
parameters:
  normalize: false
slices:
- sources:
  - layer_range: [0, 80]
    model: nvidia/Llama-3.1-Nemotron-70B-Instruct-HF+mlabonne/Llama-3-70B-Instruct-abliterated-LORA
    parameters:
      weight: 1.0

```

### Acknowlegements

Thanks to [@mlabonne](https://huggingface.co/mlabonne), [@grimjim](https://huggingface.co/grimjim), and [@failspy](https://huggingface.co/failspy) for pioneering this technique for uncensoring models.

Compute provided by [Hetzner](https://www.hetzner.com/) and funded by [Schneewolf Labs](https://schneewolflabs.com/).
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_nbeerbower__Llama-3.1-Nemotron-lorablated-70B)

|      Metric       |Value|
|-------------------|----:|
|Avg.               |33.69|
|IFEval (0-Shot)    |71.47|
|BBH (3-Shot)       |48.06|
|MATH Lvl 5 (4-Shot)|23.34|
|GPQA (0-shot)      | 0.89|
|MuSR (0-shot)      |14.92|
|MMLU-PRO (5-shot)  |43.46|