Jeff PRO

koolhug's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model 11 days ago

featherless-ai/Qwerky-72B

Text Generation • Updated 10 days ago • 1.38k • 48

liked 2 models 3 months ago

bartowski/HuatuoGPT-o1-8B-GGUF

Text Generation • Updated Dec 31, 2024 • 4.75k • 10

FreedomIntelligence/HuatuoGPT-o1-8B

Text Generation • Updated Dec 30, 2024 • 3.24k • 40

upvoted a paper 3 months ago

HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs

Paper • 2412.18925 • Published Dec 25, 2024 • 100

liked 2 models 4 months ago

answerdotai/ModernBERT-base

Fill-Mask • Updated Jan 15 • 3.26M • 816

instructlab/granite-3.0-8b-lab-community

Text Generation • Updated Dec 18, 2024 • 45 • 5

liked a model 6 months ago

lamm-mit/x-lora

Updated May 15, 2024 • 14

upvoted 2 collections 6 months ago

LayerSkip

Collection

Models continually pretrained using LayerSkip - https://arxiv.org/abs/2404.16710 • 8 items • Updated Nov 21, 2024 • 47

Reasoning

Collection

151 items • Updated Apr 6, 2024 • 30

liked 2 datasets 6 months ago

lmarena-ai/arena-human-preference-55k

Viewer • Updated May 17, 2024 • 57.5k • 600 • 142

lmsys/lmsys-chat-1m

Viewer • Updated Jul 27, 2024 • 1M • 4.07k • 654

reacted to mlabonne's post with ❤️ 6 months ago

view post

Post

19115

✂️ 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

• 

• 
• 
• 
• 26 replies

·

🔥

27

27

❤️

9

9

🚀

8

8

👍

7

7

👀

6

6

😎

6

6

🧠

4

4

🤝

4

4

🤯

3

3

😔

3

3

+

Reply

liked 2 models 6 months ago

mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated

Text Generation • Updated Sep 14, 2024 • 26.9k • 154

openai/whisper-large-v3-turbo

Automatic Speech Recognition • Updated Oct 4, 2024 • 3.72M • • 2.23k

liked 4 models 7 months ago

Narrativaai/BioGPT-Large-finetuned-chatdoctor

Text Generation • Updated May 3, 2023 • 24 • 36

Falconsai/medical_summarization

Summarization • Updated Jan 20, 2024 • 3.53k • • 133

Davlan/bert-base-multilingual-cased-ner-hrl

Token Classification • Updated Nov 11, 2024 • 338k • • 70

microsoft/Phi-3.5-mini-instruct

Text Generation • Updated Mar 2 • 254k • • 849