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
98.8K Pulls Updated 3 months ago
17 Tags
5084e77c1e10 • 40GB •
3 months ago
5084e77c1e10 • 40GB •
3 months ago
e04ae4d96458 • 141GB •
3 months ago
8fe3c853372c • 26GB •
3 months ago
9c6705916e06 • 37GB •
3 months ago
a6b22bd90923 • 34GB •
3 months ago
21f651100031 • 31GB •
3 months ago
5084e77c1e10 • 40GB •
3 months ago
b72afde19a06 • 44GB •
3 months ago
be39ad6154f4 • 43GB •
3 months ago
420791ca0c2a • 40GB •
3 months ago
99e430b53c8b • 49GB •
3 months ago
41bd1db0b708 • 53GB •
3 months ago
f537d644476a • 50GB •
3 months ago
84a4d89b332c • 49GB •
3 months ago
77fecce26024 • 58GB •
3 months ago
159e9e593c44 • 75GB •
3 months ago