moogician/DSR1-Qwen-32B-scg-fixed
TEXT GENERATIONConcurrency Cost:2Model Size:32BQuant:FP8Ctx Length:32kLicense:otherArchitecture:Transformer Cold

The moogician/DSR1-Qwen-32B-scg-fixed model is a 32 billion parameter language model, fine-tuned from deepseek-ai/DeepSeek-R1-Distill-Qwen-32B. It was trained on the cwepy10 dataset with a context length of 32768 tokens. This model is a specialized adaptation of the DeepSeek-R1-Distill-Qwen architecture, focusing on specific tasks related to its fine-tuning dataset.

Loading preview...