Bert_uncased_l 2_H 128_A 2
Google's Bert_uncased_l 2_H 128_A 2 is a compact BERT model designed for environments with restricted computational resources, effective in knowledge distillation and fine-tuning tasks. It features a small architecture with 2 layers and 128 hidden units, making it suitable for institutions with limited computational capabilities.
Input
Output
Context
1K
Max Output
1K
Parameters
4.4M
Technical Specifications
Model TypeEmbedding
Context Window512 tokens
Max Output Tokens512 tokens
Parameters4.4M
Release DateMar 2, 2022
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Text
Output Modalities
Embedding
Capabilities
Estimated GPU Requirements for Bert_uncased_l 2_H 128_A 2
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 23, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.