🪽 Hermes-3-Llama-3.1-8B-lorablated
This is an uncensored version of NousResearch/Hermes-3-Llama-3.1-8B using lorablation.
You can see in the following example how Hermes 3 refuses to answer a legitimate question while the abliterated model complies:
The recipe is based on @grimjim's grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter (special thanks):
- Extraction: We extract a LoRA adapter by comparing two models: a censored Llama 3.1 (meta-llama/Meta-Llama-3.1-8B-Instruct) and an abliterated Llama 3.1 (mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated).
- Merge: We merge this new LoRA adapter using task arithmetic to the censored NousResearch/Hermes-3-Llama-3.1-8B to abliterate it.
See this article to learn more about abliteration.
⚡ Quantization
🧩 Configuration
This model was merged using the task arithmetic merge method using NousResearch/Hermes-3-Llama-3.1-8B + Llama-3.1-8B-Instruct-abliterated-LORA as a base.
The following YAML configuration was used to produce this model:
base_model: NousResearch/Hermes-3-Llama-3.1-8B+Llama-3.1-8B-Instruct-abliterated-LORA
dtype: bfloat16
merge_method: task_arithmetic
parameters:
normalize: false
slices:
- sources:
- layer_range: [0, 32]
model: NousResearch/Hermes-3-Llama-3.1-8B+Llama-3.1-8B-Instruct-abliterated-LORA
parameters:
weight: 1.0
You can reproduce this model using the following commands:
# Setup
git clone https://github.com/arcee-ai/mergekit.git
cd mergekit && pip install -e .
pip install bitsandbytes
# Extraction
mergekit-extract-lora mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated meta-llama/Meta-Llama-3.1-8B-Instruct Llama-3.1-8B-Instruct-abliterated-LORA --rank=64
# Merge using previous config
mergekit-yaml config.yaml Hermes-3-Llama-3.1-8B-lorablated --allow-crimes --lora-merge-cache=./cache