Mohsen Dowlatshah

mones2222's activity

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

upvoted an article about 2 months ago

view article

Article

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

• 
• 
• +2

May 23

•

170

upvoted an article 3 months ago

view article

Article

🥬 TinyLettuce: Efficient Hallucination Detection with 17–68M Encoders

• 

Aug 31

•

15

upvoted 4 articles 4 months ago

view article

Article

From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels

• 
• 

Aug 18

•

88

view article

Article

Vision Language Model Alignment in TRL ⚡️

• 
• 
• +3

Aug 7

•

101

view article

Article

Introducing AI Sheets: a tool to work with datasets using open AI models!

• 
• 
• +4

Aug 8

•

106

view article

Article

TextQuests: How Good are LLMs at Text-Based Video Games?

• 
• 

Aug 12

•

36

reacted to mlabonne's post with 👍 4 months ago

view post

Post

18225

✂️ AutoAbliteration

I made a Colab notebook to automatically abliterate models.

It's quite general, so you can do interesting stuff like blocking a given language in the model outputs.

💻 Colab: https://colab.research.google.com/drive/1RmLv-pCMBBsQGXQIM8yF-OdCNyoylUR1?usp=sharing

See translation

• 

• 
• 1 reply

·

👍

49

49

🔥

20

20

❤️

10

10

😎

8

8

🚀

5

5

+

Reply

upvoted an article 4 months ago

view article

Article

Uncensor any LLM with abliteration

• 

Jun 13, 2024

•

733

liked a Space 4 months ago

Running

587

Scaling test-time compute

📈

587

Implement test-time compute scaling for math problems

upvoted 10 articles 4 months ago

view article

Article

Preference Tuning LLMs with Direct Preference Optimization Methods

• 
• 
• +3

Jan 18, 2024

•

75

view article

Article

Illustrating Reinforcement Learning from Human Feedback (RLHF)

• 
• 
• +2

Dec 9, 2022

•

378

view article

Article

SmolLM3: smol, multilingual, long-context reasoner

• 
• 
• +21

Jul 8

•

736

view article

Article

Consilium: When Multiple LLMs Collaborate

• 

Jul 17

•

29

view article

Article

Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face

• 
• 
• +3

Jul 29

•

203

view article

Article

Ettin Suite: SoTA Paired Encoders and Decoders

• 
• 
• +4

Jul 16

•

77

view article

Article

ScreenEnv: Deploy your full stack Desktop Agent

• 
• 

Jul 10

•

74

view article

Article

Building the Hugging Face MCP Server

• 
• 
• +2

Jul 10

•

66

view article

Article

Efficient MultiModal Data Pipeline

• 
• 
• +3

Jul 8

•

59

view article

Article

(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware

• 
• 
• +3

Jun 19

•

95

liked a Space 5 months ago

Running

3.56k

The Ultra-Scale Playbook

🌌

3.56k

The ultimate guide to training LLM on large GPU Clusters