devkit/
L1-Qwen-1.5B-Max

68 9 months ago

Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

3 models

L1-Qwen-1.5B-Max:latest
c3bd8a8cdfa1 • 1.9GB • 128K context window •
Text input • 9 months ago
L1-Qwen-1.5B-Max:q8_0
c3bd8a8cdfa1 • 1.9GB • 128K context window •
Text input • 9 months ago
L1-Qwen-1.5B-Max:f16
ad31c098d9eb • 3.6GB • 128K context window •
Text input • 9 months ago