ethicalabs/Kurtis-E1.1-Qwen2.5-3B-Instruct
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:Mar 30, 2025License:mitArchitecture:Transformer0.0K Open Weights Warm

The ethicalabs/Kurtis-E1.1-Qwen2.5-3B-Instruct is a 3.09 billion parameter instruction-tuned causal language model based on the Qwen2.5 architecture, fine-tuned with the Flower framework. This model demonstrates strong performance across various general knowledge and reasoning benchmarks, including MMLU (65.22%) and ARC-Easy (77.10%). With a context length of 32768 tokens, it is suitable for applications requiring robust understanding and generation of text in a compact form factor.

Loading preview...