Dokyoon's picture

68 270

Dokyoon

leeloolee

·

Eruly

AI & ML interests

ai

Recent Activity

liked a model 3 days ago

unsloth/DeepSeek-R1-BF16

reacted to abidlabs's post with 🔥 6 days ago

Hi folks! Excited to share a new feature from the Gradio team along with a tutorial. If you don't already know, Gradio is an open-source Python library used to build interfaces for machine learning models. Beyond just creating UIs, Gradio also exposes API capabilities and now, Gradio apps can be launched Model Context Protocol (MCP) servers for LLMs. If you already know how to use Gradio, there are only two additional things you need to do: * Add standard docstrings to your function (these will be used to generate the descriptions for your tools for the LLM) * Set `mcp_server=True` in `launch()` Here's a complete example (make sure you already have the latest version of Gradio installed): ```py import gradio as gr def letter_counter(word, letter): """Count the occurrences of a specific letter in a word. Args: word: The word or phrase to analyze letter: The letter to count occurrences of Returns: The number of times the letter appears in the word """ return word.lower().count(letter.lower()) demo = gr.Interface( fn=letter_counter, inputs=["text", "text"], outputs="number", title="Letter Counter", description="Count how many times a letter appears in a word" ) demo.launch(mcp_server=True) ``` This is a very simple example, but you can add the ability to generate Ghibli images or speak emotions to any LLM that supports MCP. Once you have an MCP running locally, you can copy-paste the same app to host it on [Hugging Face Spaces](https://huggingface.co/spaces/) as well. All free and open-source of course! Full tutorial: https://www.gradio.app/guides/building-mcp-server-with-gradio

upvoted a collection 11 days ago

🔍 Interpretability & Analysis of LMs

View all activity

Organizations

leeloolee's activity

upvoted a collection 11 days ago

🔍 Interpretability & Analysis of LMs

Outstanding research in LM interpretability and evaluation, summarized • 109 items • Updated 8 days ago • 100

upvoted a paper 22 days ago

Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models

Paper • 2504.03624 • Published Apr 4 • 13

upvoted a collection 23 days ago

LLM2Vec

16 items • Updated Oct 8, 2024 • 46

upvoted 2 papers about 2 months ago

Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't

Paper • 2503.16219 • Published Mar 20 • 48

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Paper • 2503.07572 • Published Mar 10 • 44

upvoted 4 papers 3 months ago

LongPO: Long Context Self-Evolution of Large Language Models through Short-to-Long Preference Optimization

Paper • 2502.13922 • Published Feb 19 • 28

s1: Simple test-time scaling

Paper • 2501.19393 • Published Jan 31 • 120

Towards Physical Understanding in Video Generation: A 3D Point Regularization Approach

Paper • 2502.03639 • Published Feb 5 • 9

DiffuEraser: A Diffusion Model for Video Inpainting

Paper • 2501.10018 • Published Jan 17 • 14

upvoted 2 papers 4 months ago

PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward Models

Paper • 2501.03124 • Published Jan 6 • 14

GUI Agents: A Survey

Paper • 2412.13501 • Published Dec 18, 2024 • 29

upvoted 2 papers 5 months ago

Multimodal Latent Language Modeling with Next-Token Diffusion

Paper • 2412.08635 • Published Dec 11, 2024 • 45

Large Multi-modal Models Can Interpret Features in Large Multi-modal Models

Paper • 2411.14982 • Published Nov 22, 2024 • 17

upvoted 2 collections 5 months ago

Multimodal-SAE

The collection of the sae that hooked on llava • 5 items • Updated Mar 4 • 8

GUI agents

A collection of papers on GUI agents • 3 items • Updated Dec 14, 2024 • 5

upvoted 3 papers 5 months ago

Granite Guardian

Paper • 2412.07724 • Published Dec 10, 2024 • 18

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published Dec 4, 2024 • 134

Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions

Paper • 2411.14405 • Published Nov 21, 2024 • 62