all AI news
Shocking: 2/3 of LLMs fail at 2K context length
Jan. 12, 2024, 1 p.m. | code_your_own_AI
code_your_own_AI www.youtube.com
My test prompt is with 5272 characters too long to upload to Youtube.
I use a prompt of 741 words, corresponding to 1254 tokens (of my adapted tokenizer).
Every tested models applies its specific tokenization.
It is amazing, that open source LLM outperform even huge commercial LLMs.
By …
characters context current jan language language models large language large language models llms placement prompt rag solution systems test token youtube
More from www.youtube.com / code_your_own_AI
Warning GPT-4o: DON'T translate to Chinese (MIT)
1 day, 21 hours ago |
www.youtube.com
CODE Fine-Tune Vision Language VLM eg PaliGemma-3B
2 days, 15 hours ago |
www.youtube.com
TURBO outperforms GPT-4o in Reasoning #gpt4o
3 days, 16 hours ago |
www.youtube.com
From Dating Apps to AI: Gen Z Edition 😆
5 days, 16 hours ago |
www.youtube.com
Do not use Llama-3 70B for these tasks ...
6 days, 14 hours ago |
www.youtube.com
New xLSTM explained: Better than Transformer LLMs?
1 week, 1 day ago |
www.youtube.com
Stealth LLM: im-a-good-gpt2-chatbot
1 week, 3 days ago |
www.youtube.com
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US