hyunseoki/verl-math-transfer-7bi-to-3bi-fix03
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Mar 27, 2026Architecture:Transformer Cold

The hyunseoki/verl-math-transfer-7bi-to-3bi-fix03 model is a 7.6 billion parameter Qwen2ForCausalLM architecture developed by hyunseoki, specifically designed for mathematical transfer learning experiments. This model represents a transfer from a 7B to a 3B configuration, focusing on improving mathematical reasoning capabilities. It is primarily intended for research and development in the domain of mathematical problem-solving and model scaling.

Loading preview...