Vinit Tavde

VinitT
·

AI & ML interests

None yet

Recent Activity

updated a Space 5 days ago
VinitT/ResearchRadar.AI
published a Space 5 days ago
VinitT/ResearchRadar.AI
updated a Space 26 days ago
VinitT/Sanskrit-Llama
View all activity

Organizations

DataScienceEngineering's profile picture AI FILMS's profile picture GEM benchmark's profile picture lora concepts library's profile picture Open-Source AI Meetup's profile picture MLX Community's profile picture

VinitT's activity

updated a Space 26 days ago
updated a Space 28 days ago
updated a Space about 1 month ago
updated a Space 3 months ago
New activity in VinitT/Llama-3.2-11B-Vision-Instruct 4 months ago

Update requirements.txt

#2 opened 4 months ago by
diabolic6045

Update app.py

1
#1 opened 4 months ago by
diabolic6045
updated a Space 4 months ago
reacted to Jaward's post with 👀 4 months ago
view post
Post
1343
Some interesting findings in this paper:
- They consider o1 a Large Reasoning Model (LRM) with a different arch from SOTA LLMs.
- Creative justifications: “It is almost as if o1 has gone from hallucinating to gaslighting!”. This is so true, I noticed also it can “hallucinate” its chain-of-thoughts lol.
- Accuracy/Cost Tradeoffs: o1 provides high accuracy but at significant computational and monetary costs due to hidden "reasoning tokens."
Paper: https://www.arxiv.org/abs/2409.13373
updated a Space 4 months ago