Large Language Models
142 views
BERT
Quick Definition
Google's bidirectional transformer for context understanding
Full Definition
Bidirectional Encoder Representations from Transformers, a Google model processing text in both directions.
Examples
search ranking, question answering, sentiment analysis
Related Terms
transformer
encoder-only
More Large Language Models Terms
Model Merging
Combining fine-tuned LLMs without additional training
Attention Head
Individual attention mechanism learning specific patterns
Positional Encoding
Incorporating token position information into transformers
RLHF
Aligning LLMs with human preferences using reinforcement learning
Streaming
Sending LLM tokens to clients as they are generated
Mistral
Efficient open-source LLMs with strong performance