-
mistralai/Mistral-7B-Instruct-v0.2
Text Generation • Updated • 925k • • 2.53k -
mistralai/Mixtral-8x7B-Instruct-v0.1
Text Generation • Updated • 626k • • 4.14k -
mistralai/Mixtral-8x7B-v0.1
Text Generation • Updated • 68.5k • 1.63k -
PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Paper • 2403.10704 • Published • 56
Molone Laveh
molonelaveh
·
AI & ML interests
convergence, multi-modality, multi-agent, LLM, research
Organizations
Collections
2
models
None public yet
datasets
None public yet