wang

David0702's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 7 days ago

StarTrek TNG Universe

Collection

Coding with Spock • 60 items • Updated Jan 13 • 1

liked a model 7 days ago

Open4bits/gpt-oss-120b-mlx-2Bit

Text Generation • 117B • Updated 7 days ago • 239 • 1

liked a model 8 days ago

nightmedia/OpenAI-gpt-oss-20B-INSTRUCT-Heretic-Uncensored-MXFP4-q8-hi-mlx

Text Generation • 21B • Updated 10 days ago • 724 • 1

liked a model 16 days ago

lmstudio-community/GLM-4.7-Flash-MLX-8bit

Text Generation • 30B • Updated 25 days ago • 1.19M • 8

upvoted a collection 10 months ago

InternVL3

Collection

34 items • Updated Sep 28, 2025 • 84

liked a Space 10 months ago

Running

Featured

508

InternVL

⚡

508

Chat with AI using text and images

upvoted a paper 10 months ago

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Paper • 2504.10479 • Published Apr 14, 2025 • 306

upvoted an article 12 months ago

view article

Article

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

• 
• 
• +1

Jan 28, 2025

•

888

upvoted an article about 1 year ago

view article

Article

From Zero to Reasoning Hero: How DeepSeek-R1 Leverages Reinforcement Learning to Master Complex Reasoning

• 

Feb 4, 2025

•

17

updated 6 models almost 2 years ago

David0702/dqn-SpaceInvadersNoFrameskip-v4

Reinforcement Learning • Updated May 7, 2024 • 1

David0702/Taxi-v3

Reinforcement Learning • Updated May 5, 2024

David0702/q-FrozenLake-v1-4x4-noSlippery

Reinforcement Learning • Updated May 5, 2024

David0702/ppo-Huggy

Reinforcement Learning • Updated May 4, 2024 • 3

David0702/ppo-LunarLander-v2

Reinforcement Learning • Updated Apr 30, 2024 • 1

David0702/ppo-LunarLander-v2-1

Reinforcement Learning • Updated Apr 30, 2024 • 2

updated a collection almost 2 years ago

RL

Collection

1 item • Updated Apr 26, 2024

upvoted a collection almost 2 years ago

DBRX

Collection

DBRX is a mixture-of-experts (MoE) large language model trained from scratch by Databricks. • 3 items • Updated Mar 27, 2024 • 96