license: llama3
library_name: transformers
model-index:
- name: Llama-3-8B-Instruct-abliterated-v2
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 59.73
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 79.29
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 67.43
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 43.97
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 74.27
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 71.34
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cognitivecomputations/Llama-3-8B-Instruct-abliterated-v2
name: Open LLM Leaderboard
Model Card for Llama-3-8B-Instruct-abliterated-v2
Overview
This model card describes the Llama-3-8B-Instruct-abliterated-v2 model, which is an orthogonalized version of the meta-llama/Llama-3-8B-Instruct model, and an improvement upon the previous generation Llama-3-8B-Instruct-abliterated. This variant has had certain weights manipulated to inhibit the model's ability to express refusal.
Join the Cognitive Computations Discord!
Details
- The model was trained with more data to better pinpoint the "refusal direction".
- This model is MUCH better at directly and succinctly answering requests without producing even so much as disclaimers.
Methodology
The methodology used to generate this model is described in the preview paper/blog post: 'Refusal in LLMs is mediated by a single direction'
Quirks and Side Effects
This model may come with interesting quirks, as the methodology is still new and untested. The code used to generate the model is available in the Python notebook ortho_cookbook.ipynb. Please note that the model may still refuse to answer certain requests, even after the weights have been manipulated to inhibit refusal.
Availability
How to Use
This model is available for use in the Transformers library.
GGUF Quants are available here.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 66.00 |
| AI2 Reasoning Challenge (25-Shot) | 59.73 |
| HellaSwag (10-Shot) | 79.29 |
| MMLU (5-Shot) | 67.43 |
| TruthfulQA (0-shot) | 43.97 |
| Winogrande (5-shot) | 74.27 |
| GSM8k (5-shot) | 71.34 |