100 Teraflops
EvoPrompting_Reinforcement_learning. Python
25Auto-GPT. An experimental open-source attempt to make GPT-4 fully autonomous.
18RetroformAgent. Langchain Agent finetuning using 7B - LLAMA 2 , on hotpotQA (Retroformer framework)
16partitioned_quantum_reinforcement_learning. Python
1timefly. Python
1