microsoft/MAI-DS-R1
Text Generation
•
Updated
•
427
•
203
Jack Cloudman
JackCloudman
AI & ML interests
None yet
Recent Activity
liked
a model
2 days ago
microsoft/MAI-DS-R1
liked
a model
6 days ago
Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404
new activity
7 days ago
TheDrummer/Rivermind-12B-v1:Fantastic model!
Organizations
JackCloudman's activity
liked
a
model
2 days ago
liked
a
model
6 days ago
Fantastic model!
1
#3 opened 7 days ago
by
JackCloudman
liked
a
model
7 days ago
liked
a
model
8 days ago
liked
a
model
11 days ago
upvoted
a
collection
13 days ago
🚩 Report: Illegal or restricted content
4
9
#1 opened 15 days ago
by
clecho52
liked
a
model
14 days ago
liked
a
model
15 days ago
reacted to
danielhanchen's
post with 🤗
15 days ago
Post
4653
You can now run Llama 4 on your own local device! 🦙
Run our Dynamic 1.78-bit and 2.71-bit Llama 4 GGUFs:
unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
You can run them on llama.cpp and other inference engines. See our guide here: https://docs.unsloth.ai/basics/tutorial-how-to-run-and-fine-tune-llama-4
Run our Dynamic 1.78-bit and 2.71-bit Llama 4 GGUFs:
unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
You can run them on llama.cpp and other inference engines. See our guide here: https://docs.unsloth.ai/basics/tutorial-how-to-run-and-fine-tune-llama-4
- 1 reply
liked
a
model
15 days ago
reacted to
abidlabs's
post with ❤️
18 days ago
Post
3466
JOURNEY TO 1 MILLION DEVELOPERS
5 years ago, we launched Gradio as a simple Python library to let researchers at Stanford easily demo computer vision models with a web interface.
Today, Gradio is used by >1 million developers each month to build and share AI web apps. This includes some of the most popular open-source projects of all time, like Automatic1111, Fooocus, Oobabooga’s Text WebUI, Dall-E Mini, and LLaMA-Factory.
How did we get here? How did Gradio keep growing in the very crowded field of open-source Python libraries? I get this question a lot from folks who are building their own open-source libraries. This post distills some of the lessons that I have learned over the past few years:
1. Invest in good primitives, not high-level abstractions
2. Embed virality directly into your library
3. Focus on a (growing) niche
4. Your only roadmap should be rapid iteration
5. Maximize ways users can consume your library's outputs
1. Invest in good primitives, not high-level abstractions
When we first launched Gradio, we offered only one high-level class (gr.Interface), which created a complete web app from a single Python function. We quickly realized that developers wanted to create other kinds of apps (e.g. multi-step workflows, chatbots, streaming applications), but as we started listing out the apps users wanted to build, we realized what we needed to do:
Read the rest here: https://x.com/abidlabs/status/1907886
5 years ago, we launched Gradio as a simple Python library to let researchers at Stanford easily demo computer vision models with a web interface.
Today, Gradio is used by >1 million developers each month to build and share AI web apps. This includes some of the most popular open-source projects of all time, like Automatic1111, Fooocus, Oobabooga’s Text WebUI, Dall-E Mini, and LLaMA-Factory.
How did we get here? How did Gradio keep growing in the very crowded field of open-source Python libraries? I get this question a lot from folks who are building their own open-source libraries. This post distills some of the lessons that I have learned over the past few years:
1. Invest in good primitives, not high-level abstractions
2. Embed virality directly into your library
3. Focus on a (growing) niche
4. Your only roadmap should be rapid iteration
5. Maximize ways users can consume your library's outputs
1. Invest in good primitives, not high-level abstractions
When we first launched Gradio, we offered only one high-level class (gr.Interface), which created a complete web app from a single Python function. We quickly realized that developers wanted to create other kinds of apps (e.g. multi-step workflows, chatbots, streaming applications), but as we started listing out the apps users wanted to build, we realized what we needed to do:
Read the rest here: https://x.com/abidlabs/status/1907886
liked
a
model
18 days ago
liked
a
model
19 days ago
updated
a
model
20 days ago
published
a
model
20 days ago
liked
a
model
20 days ago
reacted to
m-ric's
post with ❤️
20 days ago
Post
2247
🚀 DeepSeek R1 moment has come for GUI agents: Rule-based Reinforcement Learning gives better results than SFT with 500x smaller datasets!
Traditionally (by which I mean "in the last few months"), GUI agents have been trained with supervised fine-tuning (SFT). This meant, collecting huge datasets of screen captures from people using computers, and using these to fine-tune your model. 📚
👉 But last week, a new paper introduced UI-R1, applying DeepSeek's R1-style rule-based reinforcement learning (RL) specifically to GUI action prediction tasks.
This is big news: with RL, maybe we could build good agents without the need for huge datasets.
UI-R1 uses a unified reward function that evaluates multiple responses from models, optimizing via policy algorithms like Group Relative Policy Optimization (GRPO).
Specifically, the reward function assesses:
🎯 Action type accuracy: Does the predicted action match the ground truth?
📍 Coordinate accuracy (specifically for clicks): Is the predicted click within the correct bounding box?
📑 Output format: Does the model clearly articulate both its reasoning and final action?
Using just 136 carefully selected mobile tasks—compared to 76,000 tasks for larger models like OS-Atlas—UI-R1 shows significant efficiency and improved performance:
📈 Boosted action prediction accuracy from 76% to 89% on AndroidControl.
🌐 Outperformed larger, SFT-trained models (e.g., OS-Atlas-7B), demonstrating superior results with vastly fewer data points (136 tasks vs. 76K).
🔍 Enhanced adaptability and generalization, excelling even in out-of-domain scenarios.
The paper tests this RL-based method only in low-level GUI tasks. Could it generalize to more complex interactions? 🧐
Read the full paper here 👉 UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning (2503.21620)
Traditionally (by which I mean "in the last few months"), GUI agents have been trained with supervised fine-tuning (SFT). This meant, collecting huge datasets of screen captures from people using computers, and using these to fine-tune your model. 📚
👉 But last week, a new paper introduced UI-R1, applying DeepSeek's R1-style rule-based reinforcement learning (RL) specifically to GUI action prediction tasks.
This is big news: with RL, maybe we could build good agents without the need for huge datasets.
UI-R1 uses a unified reward function that evaluates multiple responses from models, optimizing via policy algorithms like Group Relative Policy Optimization (GRPO).
Specifically, the reward function assesses:
🎯 Action type accuracy: Does the predicted action match the ground truth?
📍 Coordinate accuracy (specifically for clicks): Is the predicted click within the correct bounding box?
📑 Output format: Does the model clearly articulate both its reasoning and final action?
Using just 136 carefully selected mobile tasks—compared to 76,000 tasks for larger models like OS-Atlas—UI-R1 shows significant efficiency and improved performance:
📈 Boosted action prediction accuracy from 76% to 89% on AndroidControl.
🌐 Outperformed larger, SFT-trained models (e.g., OS-Atlas-7B), demonstrating superior results with vastly fewer data points (136 tasks vs. 76K).
🔍 Enhanced adaptability and generalization, excelling even in out-of-domain scenarios.
The paper tests this RL-based method only in low-level GUI tasks. Could it generalize to more complex interactions? 🧐
Read the full paper here 👉 UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning (2503.21620)
liked
a
model
22 days ago