Alexandru Lupoi

drwlf's activity

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

upvoted an article 4 months ago

view article

Article

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

• 
• 
• +7

Jun 3

•

299

upvoted 2 collections 6 months ago

[New] AI Technologies & Services

Collection

'OpenFree AI' 커뮤니티: https://discord.gg/openfreeai • 188 items • Updated 18 days ago • 22

Thinking / Reasoning Models - Reg and MOEs.

Collection

QwQ,DeepSeek, EXONE, DeepHermes, and others "thinking/reasoning" AIs / LLMs in regular model type, MOE (mix of experts), and Hybrid model formats. • 178 items • Updated 14 days ago • 14

upvoted an article 7 months ago

view article

Article

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

• 
• 
• +2

May 23

•

170

upvoted a paper 7 months ago

MedCaseReasoning: Evaluating and learning diagnostic reasoning from clinical case reports

Paper • 2505.11733 • Published May 16 • 7

upvoted an article 8 months ago

view article

Article

Uncensor any LLM with abliteration

• 

Jun 13, 2024

•

744

upvoted 2 collections 8 months ago

Unsloth 4-bit Dynamic Quants

Collection

Unsloths Dynamic 4bit Quants selectively skips quantizing certain parameters; greatly improving accuracy while only using <10% more VRAM than BnB 4bit • 28 items • Updated 1 day ago • 91

Gemma 3

Collection

All versions of Google's new multimodal models including QAT in 1B, 4B, 12B, and 27B sizes. In GGUF, dynamic 4-bit and 16-bit formats. • 55 items • Updated 1 day ago • 100

upvoted a collection 9 months ago

Llama 3.2

Collection

Meta's new Llama 3.2 vision and text models including 1B, 3B, 11B and 90B. Includes GGUF, 4-bit bnb and original versions. • 27 items • Updated 1 day ago • 68

upvoted a paper 9 months ago

Hermes 3 Technical Report

Paper • 2408.11857 • Published Aug 15, 2024 • 56