Large Language Models (LLMs)

LLM - History

Subpages

Transformer based:

• Generative Pre-trained Transformer (GPT)

  List indent undo

  • AI Agents／Assistants
  • Alpaca
  • BERT (Bidirectional Encoder Representations from Transformers)
  • Claude
  • DocsGPT
  • Evolutionary Scale Model 3 (ESM-3) Evolution Language Model
  • GLM-4-Voice
  • GPT-Generated Unified Format (GGUF)
  • Kotaemon
  • LLaMA
  • LLM Interpretability
  • LM Studio
  • MLX
  • ollama
  • Pathways Language Model (PaLM)
  • Retrieval-Augmented Generation (RAG)
  • Ultravox
  • vLLM

• BLOOM
• Ernie 3.0 Titan
• Claude

Diffusion based:

• Gemini Diffusion - Google
• Mercury Coder
• Seed Diffusion - ByteDance

LLM - Challenges

Known challenges of LLMs include:

• Presenting false information when it does not have the answer.
• Presenting out-of-date or generic information when the user expects a specific, current response.
• Creating a response from non-authoritative sources.
• Creating inaccurate responses due to terminology confusion, wherein different training sources use the same terminology to talk about different things