Cohee/distilbert-base-uncased-go-emotions-onnx
Text Classification
•
Updated
•
9.78k
•
6
junk
pornjunk
·
AI & ML interests
None yet
Recent Activity
liked
a model
about 14 hours ago
Cohee/distilbert-base-uncased-go-emotions-onnx
liked
a model
2 days ago
UnfilteredAI/NSFW-3B
liked
a dataset
8 days ago
YeungNLP/firefly-train-1.1M
Organizations
None yet
pornjunk's activity
liked
a
model
about 14 hours ago
liked
a
model
2 days ago
liked
a
dataset
8 days ago
liked
a
dataset
14 days ago
liked
a
dataset
15 days ago
reacted to
mlabonne's
post with 🔥
15 days ago
Post
18928
✂️ Uncensor any LLM with abliteration
I wrote an article about abliteration and how NeuralDaredevil-8B was created. Beyond removing alignment, I believe it's an interesting technique with a lot of potential. It's basically fine-tuning without retraining.
In this article, we see how it works, implement it in Google Colab, and heal the abliterated model to recover the performance drop due to this technique. The final model is an uncensored and high-quality model with the highest MMLU score on the Open LLM Leaderboard (8B category).
https://huggingface.co/blog/mlabonne/abliteration
I wrote an article about abliteration and how NeuralDaredevil-8B was created. Beyond removing alignment, I believe it's an interesting technique with a lot of potential. It's basically fine-tuning without retraining.
In this article, we see how it works, implement it in Google Colab, and heal the abliterated model to recover the performance drop due to this technique. The final model is an uncensored and high-quality model with the highest MMLU score on the Open LLM Leaderboard (8B category).
https://huggingface.co/blog/mlabonne/abliteration
- 26 replies
liked
a
dataset
15 days ago
liked
a
model
15 days ago
liked
a
dataset
15 days ago