A high-performing model trained with a new technique called Reflection-tuning that teaches a LLM to detect mistakes in its reasoning and correct course.

70b

96.5K 2 months ago

17 Tags
5084e77c1e10 • 40GB • 2 months ago
5084e77c1e10 • 40GB • 2 months ago
e04ae4d96458 • 141GB • 2 months ago
8fe3c853372c • 26GB • 2 months ago
9c6705916e06 • 37GB • 2 months ago
a6b22bd90923 • 34GB • 2 months ago
21f651100031 • 31GB • 2 months ago
5084e77c1e10 • 40GB • 2 months ago
b72afde19a06 • 44GB • 2 months ago
be39ad6154f4 • 43GB • 2 months ago
420791ca0c2a • 40GB • 2 months ago
99e430b53c8b • 49GB • 2 months ago
41bd1db0b708 • 53GB • 2 months ago
f537d644476a • 50GB • 2 months ago
84a4d89b332c • 49GB • 2 months ago
77fecce26024 • 58GB • 2 months ago
159e9e593c44 • 75GB • 2 months ago