Mimi's Notebook
CtrlK
MimeusGithub
  • Experiments
    • Large Language Models
      • Attentions, attentions!
        • Attention Rank Learner
        • Graph Networks with Attention
      • Summary of Attempted Methods in Steering LLMs
        • Steering LLM: Decoder Block + Logit Scores Manipulation
      • Briefing Similarity Scoring Methods of Contextual Embeddings
      • GPT2 Transformer Attention Block Analysis
      • Cache Trails
    • Speech Models
      • Text to speech models
    • Multimodal Architectures
      • Tarot Spread Recognition
  • AI Development
    • Streaming Inference Models
    • Action Space: MCP Servers
  • Programming
    • Flutter & Dart
      • Fundamentals - Widgets
  • Quicklinks
    • Github
    • Wandb
    • Hugging Face
    • About Me
Powered by GitBook
Page cover
On this page
  1. Experiments

Large Language Models

This section includes analysis on Large Language Model architectures, specifically focusing on GPT-2.

Dependencies

The following Python libraries are required for the tests in this section's subpages:

transformers 
sentence-transformers 
torch 
numpys 
pandas 
datasets 

NextAttentions, attentions!

Last updated 4 months ago