-
mistralai/Mistral-7B-Instruct-v0.2
Text Generation • Updated • 4.99M • • 2.61k -
mistralai/Mixtral-8x7B-Instruct-v0.1
Text Generation • Updated • 4.38M • • 4.26k -
mistralai/Mixtral-8x7B-v0.1
Text Generation • Updated • 4.02M • 1.66k -
PERL: Parameter Efficient Reinforcement Learning from Human Feedback
Paper • 2403.10704 • Published • 57
Molone Laveh PRO
molonelaveh
·
AI & ML interests
convergence, multi-modality, multi-agent, LLM, research
Recent Activity
liked
a model
about 14 hours ago
nvidia/Cosmos-1.0-Guardrail
liked
a model
about 14 hours ago
nvidia/Cosmos-1.0-Autoregressive-4B
liked
a model
about 14 hours ago
nvidia/Cosmos-1.0-Diffusion-7B-Text2World
Organizations
Collections
2
models
None public yet
datasets
None public yet