Mercury: New Generation of Large Language Models for Coding Applications
By
PaulHoule
10mo ago· 2 min readenNews
85/100
Golden Brown
Bagelometer↗
Pulled from the oven just right. Trustworthy, fact-dense, deeply satisfying.
Score85TypenewsSentimentpositive
Summary
Mercury is a new generation of large language models based on diffusion, designed for coding applications. It includes Mercury Coder Mini and Small, setting a new state-of-the-art in speed and quality. Independent evaluations show significant performance improvements over existing models.
Key quotes
· 3 pulledMercury Coder Mini and Mercury Coder Small achieve state-of-the-art throughputs of 1109 tokens/sec and 737 tokens/sec, respectively, on NVIDIA H100 GPUs.
We also release a public API at https://platform.inceptionlabs.ai/ and free playground at https://chat.inceptionlabs.ai
These models set a new state-of-the-art on the speed-quality frontier.
We present Mercury, a new generation of commercial-scale large language models (LLMs) based on diffusion. These models are parameterized via the Transformer architecture and trained to predict multiple tokens in parallel. In this report, we detail Mercury
