jjzha/Qwen2.5-14B-Instruct-rt-2708
TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kLicense:mitArchitecture:Transformer0.0K Open Weights Cold

jjzha/Qwen2.5-14B-Instruct-rt-2708 is a 14.8 billion parameter instruction-tuned language model, fine-tuned by independent contributors on the Qwen2.5-14B-Instruct base. This model specializes in English text generation with enhanced factual reasoning, building upon the jjzha/rt-2708 dataset. It is designed for tasks requiring improved factual accuracy and logical consistency, making it suitable for research and assistant-like applications. The model maintains a 131072 token context length and is released under the Apache 2.0 license.

Loading preview...