Blair Sadewitz's picture

Blair Sadewitz

tachyphylaxis

·

AI & ML interests

None yet

Recent Activity

replied to mlabonne's post about 1 month ago

✂️ 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

liked a dataset about 2 months ago

tachyphylaxis/The-Mind-Is-A-Metaphor

liked a model about 2 months ago

nbeerbower/Llama3.1-Gutenberg-Doppel-70B

View all activity

Organizations

None yet

models 10

tachyphylaxis/Llama-3.1-Spellbound-Storywriter-70B-Instruct-abliterated-FP8-Dynamic

Updated Oct 8 • 98

tachyphylaxis/Llama-3.1-Spellbound-Storywriter-70B-Instruct-abliterated

Updated Oct 3 • 72

tachyphylaxis/Sao10K_L3.1-70B-Hanami-x1-EETQ

Updated Sep 12 • 3

tachyphylaxis/Meta-Llama-3.1-Chat-Uncensored

Text Generation • Updated Aug 1 • 149 • 3

tachyphylaxis/opus-v1.2-70b-marlin

Text Generation • Updated Apr 19 • 6

tachyphylaxis/Merged-Vicuna-RP-Stew-34B-GGUF

Updated Mar 3 • 8 • 1

tachyphylaxis/deepsex-34b-llamafied

Text Generation • Updated Feb 24 • 11

tachyphylaxis/deepsex-34b_safetensors

Feature Extraction • Updated Feb 22 • 4

tachyphylaxis/QuartetAnemoi-70B-t0.0001-AWQ

Text Generation • Updated Feb 18 • 10 • 1

tachyphylaxis/NyakuraV2-34B-Yi-Llama-GGUF

Updated Dec 3, 2023 • 6

datasets 1

tachyphylaxis/The-Mind-Is-A-Metaphor

Viewer • Updated Jan 26 • 14.9k • 61 • 4