Thinh Le's picture

Thinh Le PRO

thinhlpg

·

thinhlpg

AI & ML interests

anime stuffs

Recent Activity

liked a dataset 3 days ago

bhavyagiri/semantic-memes

liked a model 3 days ago

Qwen/Qwen2-1.5B-Instruct

liked a model 3 days ago

deepseek-ai/DeepSeek-R1

View all activity

Organizations

thinhlpg's activity

upvoted a collection 7 days ago

MoshiVis v0.1

MoshiVis is a Vision Speech Model built as a perceptually-augmented version of Moshi v0.1 for conversing about image inputs • 8 items • Updated 9 days ago • 16

upvoted an article 7 days ago

Article

Faster fine-tuning using TRL & Unsloth

Jan 10, 2024

• 55

upvoted an article 11 days ago

Article

Open-R1: a fully open reproduction of DeepSeek-R1

Jan 28

• 828

upvoted an article about 1 month ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

Feb 20

• 219

upvoted an article 2 months ago

Article

AI Agents Are Here. What Now?

Jan 13

• 73

upvoted a paper 2 months ago

Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese

Paper • 2408.12480 • Published Aug 22, 2024 • 23

upvoted a collection 3 months ago

🍓 Ichigo v0.5

The experimental family designed to train LLMs to understand sound natively. • 1 item • Updated Dec 29, 2024 • 3

upvoted 2 articles 6 months ago

Article

Welcome, Gradio 5

Oct 9, 2024

• 128

Article

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

May 1, 2024

• 74

upvoted a collection 6 months ago

Molmo

Artifacts for open multimodal language models. • 5 items • Updated 17 days ago • 299

upvoted an article 7 months ago

Article

Introducing Snowball Fight ☃️, our First ML-Agents Environment

Dec 2, 2021

• 2

upvoted a paper 8 months ago

SAM 2: Segment Anything in Images and Videos

Paper • 2408.00714 • Published Aug 1, 2024 • 114

upvoted 2 collections 8 months ago

Reading Papers

227 items • Updated 30 days ago • 10

Dataset generation

126 items • Updated Jul 22, 2024 • 26