32 10 33

fs

failspy

failspy

AI & ML interests

None yet

Recent Activity

liked a model 18 days ago

mlabonne/gemma-3-27b-it-abliterated-GGUF

replied to mlabonne's post 5 months 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

upvoted a collection 6 months ago

Molmo

View all activity

Organizations

failspy's activity

liked a model 18 days ago

mlabonne/gemma-3-27b-it-abliterated-GGUF

Image-Text-to-Text • Updated 4 days ago • 46.5k • 45

liked a model 7 months ago

grimjim/Llama-3.1-8B-Instruct-abliterated_via_adapter-GGUF

Text Generation • Updated Sep 4, 2024 • 524 • 26

liked a Space 8 months ago

747

UGI Leaderboard

📢

Uncensored General Intelligence Leaderboard

liked 4 models 8 months ago

liked a model 9 months ago

anakin87/yo-Llama-3-8B-Instruct

Text Generation • Updated Jul 2, 2024 • 25 • 7

liked a dataset 9 months ago

Salesforce/xlam-function-calling-60k

Viewer • Updated Jan 24 • 60k • 2.87k • 431

liked 10 models 10 months ago

microsoft/Florence-2-base-ft

Image-Text-to-Text • Updated Jul 20, 2024 • 141k • 108

microsoft/Florence-2-large-ft

Image-Text-to-Text • Updated Jul 20, 2024 • 273k • 342

microsoft/Florence-2-base

Image-Text-to-Text • Updated Nov 4, 2024 • 757k • 249

microsoft/Florence-2-large

Image-Text-to-Text • Updated Dec 8, 2024 • 1.3M • 1.5k

Xenova/Nemotron-4-340B-Instruct-Tokenizer

Updated Jun 15, 2024 • 6

cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated

Text Generation • Updated Jun 3, 2024 • 1.78k • 18

OwenArli/ArliAI-Llama-3-8B-Cumulus-v1.0

Text Generation • Updated Jul 7, 2024 • 11 • 6

OwenArli/ArliAI-Llama-3-8B-Cumulus-v1.0-GGUF

Updated Jul 7, 2024 • 233 • 4

alpindale/WizardLM-2-8x22B

Text Generation • Updated Sep 14, 2024 • 2.07k • • 399

mlabonne/NeuralDaredevil-8B-abliterated

Text Generation • Updated Aug 27, 2024 • 16.7k • 200

liked a Space 10 months ago

12.9k

Open LLM Leaderboard

🏆

Track, rank and evaluate open LLMs and chatbots