Loading...
Market
Will Arctic-SnowCoder-1.3B be used in a winning submission for a major coding competition by mid-2024?
3
Resolution / Starting Odds
Yes • 50%
No • 50%
Official results from major coding competitions (e.g., ACM ICPC, Codeforces contests)
Story
Snowflake AI's Arctic-SnowCoder-1.3B Sets SOTA with 36% Higher Performance in Code Models
Sep 6, 2024, 05:05 PM
Snowflake AI Research has introduced Arctic-SnowCoder-1.3B, a new 1.3 billion parameter model that sets the state-of-the-art (SOTA) among small language models for code. The model is trained in three phases: general pretraining on 500 billion tokens of raw code data, followed by continued pretraining on high-quality data, and finally, fine-tuning on domain-specific data. Arctic-SnowCoder-1.3B outperforms larger 1 trillion token models by 36% in code generation tasks. The model uses a total of 555 billion tokens in its training process. The research was conducted by Snowflake AI Research in collaboration with the University of Illinois at Urbana-Champaign, with contributions from Y Wei, H Han, and R Samdani.
View original story
Similar markets
Yes • 50%
No • 50%
Yes • 50%
No • 50%
Yes • 50%
No • 50%
Llama 3.1 8B • 25%
GPT-4 • 25%
Llama 3.1 70B • 25%
Other • 25%
Yes • 50%
No • 50%
Yes • 50%
No • 50%
Google DeepMind • 25%
OpenAI • 25%
Microsoft AI • 25%
Other • 25%
Yes • 50%
No • 50%
Turing Award • 33%
Nobel Prize • 33%
Breakthrough Prize • 33%