Transformer Taxonomy A fantastic literature review of transformers. it covers 22 transformer-based models, 11 architectural changes, post pre-training techniques, training techniques, and other relevant techniques from recent papers. A quick example of models/techniques
LLMS
-
Llama 2 70B Updated with System Prompt Control
By
–
Ahoy mateys! We've updated Llama 2 70B to expose the system_prompt, giving you more control over the output. https://
replicate.com/p/tyjeiltbkqsi
rmlxvwvdr4bpsy
… -
Stability AI Launches FreeWilly1 and FreeWilly2 LLMs
By
–
Introducing FreeWilly1 and FreeWilly2 – The latest groundbreaking LLMs from Stability AI's and @carperai lab! Open access and remarkable versatility. #AI #LLMs #OpenAccess #StabilityAI https://
bit.ly/3q1cCx2 -
LangChain Deprecation PR: Initial Implementation Discussion
By
–
initial pr (not deprecating yet, just getting ready for it): https://
github.com/hwchase17/lang
chain/pull/8092
… would love your thoughts -
Llamas Take Over Hugging Face Hub Platform
By
–
ok so llamas have taken control of the @huggingface hub…
-
Dario Amodei discusses AI safety and Anthropic’s mission
By
–
Our CEO Dario went on Hard Fork this week to discuss AI safety, his journey to starting Anthropic, and http://
Claude.ai. Listen here! https://
nytimes.com/2023/07/21/pod
casts/dario-amodei-ceo-of-anthropic-on-the-paradoxes-of-ai-safety-and-netflixs-deep-fake-love.html
… -
Sergey Brin Returns to Google AI Development with Gemini
By
–
https://
wsj.com/articles/serge
y-brin-google-ai-gemini-1b5aa41e
… -
Meta Llama2 Open-Source AI Model Transforms Business Landscape
By
–
Meta's #Llama2 is here! An open-source AI model rivaling proprietary giants. Dive into its transformative impact for businesses in Josh Poduska's latest piece! #AIRevolution
-
Strengthening LLM Lawsuits Through Critical Feedback Analysis
By
–
To be clear, I don't believe it's beneficial for anyone to blindly support lawsuits when there are improvements to be made. It's not just this one but the LLM one v OpenAI particularly. Criticism, regardless who it's from, should be integrated to make the complaints stronger…
-
FLASK: Fine-Grained Language Model Evaluation Based on Alignment Skills
By
–
FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets Ye et al.: https://
arxiv.org/abs/2307.10928 #ArtificialIntelligence #DeepLearning #MachineLearning