Mistral Agents
mistral.ai161 points·by eitanturok··42 comments
HumanEval is saturated: new coding LLM benchmark released
bigcode-bench.github.io1 points·by eitanturok··0 comments
Jamba: A Hybrid Transformer-Mamba Language Model
arxiv.org74 points·by eitanturok··6 comments
Are there certain types of failures that pre-training alone cannot help with?
gradientscience.org2 points·by eitanturok··0 comments
LLMs: Speeding up ALiBi by 3-5x with a hardware-efficient implementation
pli.princeton.edu2 points·by eitanturok··1 comments