continuum-ai/qwen2.5-3b-general-forged
TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:Mar 27, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The continuum-ai/qwen2.5-3b-general-forged model is a Qwen2.5-3B variant developed by continuum-ai, optimized through a 30% head pruning and retraining process using Experiential Plasticity. This process resulted in a 0.4% improvement in perplexity (from 2.30 to 2.29) while significantly reducing its parameter count. It is designed for general language tasks and is notable for its cryptographic provenance via the ForgeAlloy chain of custody, ensuring verifiable claims about its development.

Loading preview...