Explore the capabilities of long context large language models in this 25-minute video from Trelis Research. Learn about the Yi 34B 200k model, compare different long context models, and understand the differences between base and chat fine-tuned versions. Discover how to perform passkey retrieval tasks using Yi 6B and Claude models. Examine the Yi 34B model's performance with 107k context length. Get hands-on guidance for inferencing Yi models using Runpod, and learn about Yi function-calling models. Access comprehensive resources for long context models and gain valuable insights into the latest advancements in LLM technology.
Really Long Context LLMs - 200k Input Tokens
Overview
Syllabus
Really long context length large language models
Video overview
Yi 200k context model
Which long context models are actually good?
Base model vs Chat fine-tuned Yi model
Passkey Retrieval on Yi 6B
Passkey retrieval for Claude
Yi 34B performance at 107k context
Inferencing Yi models with Runpod
Yi Function-calling models
Long Context Model Resources
Video Summary
Taught by
Trelis Research
Related Courses
-
Advanced Fine-Tuning Techniques for Long Context Summarization
-
Yi 34B: The Rise of Powerful Mid-Sized Models - Base, 200k, and Chat
-
Fundamentals of AI Agents Using RAG and LangChain
-
LLMs: Understanding Temperature and Context Length of GPT Models
-
Improved Retrieval Augmented Generation with ALL-SORT - Advanced Techniques
-
How to Code Long-Context LLMs - LongLoRA Implementation with Llama 2 100K
