tinycompany/SigmaBoi-bge-m3

TEXT GENERATIONConcurrency Cost:1Model Size:3.1BQuant:BF16Ctx Length:32kPublished:Mar 8, 2025License:mitArchitecture:Transformer Open Weights Cold

SigmaBoi-bge-m3 is a 3.1 billion parameter model developed by tinycompany, featuring a context length of 32768 tokens. This model is characterized by its reported mean perplexity of 1922.9335270716385. Its primary use case appears to be general language understanding, with a focus on performance metrics.

Loading preview...

Overview

SigmaBoi-bge-m3 is a 3.1 billion parameter model from tinycompany, designed with a substantial context length of 32768 tokens. The model's reported mean perplexity is 1922.9335270716385, indicating its performance in language modeling tasks.

Key Capabilities

  • Large Context Window: Supports processing up to 32768 tokens, enabling handling of extensive inputs.
  • Performance-Oriented: The model's primary focus, as highlighted in its documentation, is on its performance characteristics, particularly its perplexity score.

Good for

  • General Language Understanding: Suitable for tasks requiring a broad understanding of text.
  • Applications Requiring Large Context: Ideal for scenarios where processing long documents or conversations is necessary due to its extended context window.