Alibaba-DAMO-Academy/Lumos-1
Updated • 51 • 11
xziayro
xziayro
AI & ML interests
None yet
Recent Activity
liked a model about 10 hours ago
Alibaba-DAMO-Academy/Lumos-1 new activity about 10 hours ago
GAIR/daVinci-MagiHuman:https://github.com/sandai/MagiCompiler seems to be private liked a model about 12 hours ago
GAIR/daVinci-MagiHumanOrganizations
liked a
model about 10 hours ago
https://github.com/sandai/MagiCompiler seems to be private
#1 opened about 10 hours ago
by xziayro
liked a
model about 12 hours ago
upvoted a paper about 12 hours ago
liked a
model about 12 hours ago
upvoted a paper about 12 hours ago
upvoted a paper 2 days ago
liked a
model 2 days ago
liked a
model 3 days ago
upvoted 2
papers 3 days ago
reactedto DedeProGames's post with 🤗 3 days ago
Post
3801
Can small models program?
Although even if they are reasoning AIs, small AIs cannot create extensive and high-quality code, at least that's what is commonly thought.
We present OrionLLM/NanoCoder-0.6b, an AI with just 600 million parameters based on qwen3-0.6b and trained with the dataset nvidia/OpenCodeReasoning.
While not good at complex code, we observed a significant improvement in code generation (especially in Python code), demonstrating that, when trained correctly, small AIs can, in fact, program.
Although even if they are reasoning AIs, small AIs cannot create extensive and high-quality code, at least that's what is commonly thought.
We present OrionLLM/NanoCoder-0.6b, an AI with just 600 million parameters based on qwen3-0.6b and trained with the dataset nvidia/OpenCodeReasoning.
While not good at complex code, we observed a significant improvement in code generation (especially in Python code), demonstrating that, when trained correctly, small AIs can, in fact, program.
- 2 replies
liked a
model 3 days ago
upvoted a paper 3 days ago
upvoted 4
papers 4 days ago
Mixture-of-Depths Attention
Paper • 2603.15619 • Published • 76
Attention Residuals
Paper • 2603.15031 • Published • 148
LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition
Paper • 2603.17965 • Published • 5
LoST: Level of Semantics Tokenization for 3D Shapes
Paper • 2603.17995 • Published • 29
liked a
model 4 days ago
upvoted a paper 4 days ago