microsoft/OmniParser-v2.0
Image-Text-to-Text
β’
Updated
β’
8.13k
β’
1.09k
JΔdrzej Grabala
jgitsolutions
AI & ML interests
Local Drive Human Overseered System of Agents, LLMs, Langchains & other useful stuff on mid-to-low-end of commercial hardware.
Recent Activity
liked
a model
2 days ago
microsoft/OmniParser-v2.0
liked
a Space
2 days ago
hf-accelerate/model-memory-usage
liked
a Space
2 days ago
huggingface/ai-deadlines
Organizations
jgitsolutions's activity
liked
a
model
2 days ago
liked
4
Spaces
2 days ago
upvoted
a
paper
4 days ago
liked
a
dataset
4 days ago
upvoted
a
paper
24 days ago
upvoted
a
collection
24 days ago
liked
a
Space
29 days ago
reacted to
chansung's
post with π
29 days ago
Post
2953
Simple Paper Review #5
I briefly reviewed the paper "SFT Memorizes, RL Generalizes," which compares SFT and RL in post-training of LLM/VLM from HKU, UC Berkeley, Google DeepMind, and New York University
The conclusion suggests SFT excels in memorization, while RL is better for generalization. However, since LLM/VLM should benefit humans beyond just generalization, a mix of SFT and RL is advisable. Typically, some SFT is followed by RL to understand prompt formats and enhance generalization through trial and error.
The study focused on one model, Llama-3.2-Vision-11B, using environments like General Points for arithmetic reasoning and V-IRL for spatial reasoning. Training data was used for both SFT and RL, with evaluations on in-distribution and out-of-distribution data to assess memorization and generalization.
I want to apply RL extensively, but it requires building a similar simulation environment. For domain-specific models, significant investment in creating a "playground" for the model is crucial, as the effort will directly influence the outcomes.
https://arxiv.org/abs/2501.17161
I briefly reviewed the paper "SFT Memorizes, RL Generalizes," which compares SFT and RL in post-training of LLM/VLM from HKU, UC Berkeley, Google DeepMind, and New York University
The conclusion suggests SFT excels in memorization, while RL is better for generalization. However, since LLM/VLM should benefit humans beyond just generalization, a mix of SFT and RL is advisable. Typically, some SFT is followed by RL to understand prompt formats and enhance generalization through trial and error.
The study focused on one model, Llama-3.2-Vision-11B, using environments like General Points for arithmetic reasoning and V-IRL for spatial reasoning. Training data was used for both SFT and RL, with evaluations on in-distribution and out-of-distribution data to assess memorization and generalization.
I want to apply RL extensively, but it requires building a similar simulation environment. For domain-specific models, significant investment in creating a "playground" for the model is crucial, as the effort will directly influence the outcomes.
https://arxiv.org/abs/2501.17161
liked
2
Spaces
about 1 month ago
upvoted
an
article
about 1 month ago
Article
Welcome to Inference Providers on the Hub π₯
β’
411
liked
a
model
about 1 month ago
liked
a
model
3 months ago
liked
4
Spaces
3 months ago
802
LTX-Video-Playground
π
Generate a video from text or an image
55
Tank War GAME
π
"One-minute creation by AI Coding Autonomous Agent MOUSE-I"
113
MOUSE-Visual AI Chatbot
π₯
Text2Visual Web Converter with AI Image Generation
2.01k
Anychat
π’
Select and view code snippets for different chat providers