Leveraging #ChatGPT to query recent #AI/#ML libraries such as LangChain is a challenge since ChatGPT's last training cut-off was in January 2022. Worry not! Check out `Chat LangChain`, a chatbot from @langchain to interact with the LangChain docs! https://
chat.langchain.com
OPEN SOURCE
-

Chat LangChain: Query AI/ML Libraries Beyond ChatGPT Training Data
By
–
-
RepoChat: GitHub Repository Chatbot with Streamlit and LLM
By
–
RepoChat is an awesome @GitHub Repo chatbot built with @Streamlit! π₯
— Charly Wargnier (@DataChaz) 15 octobre 2023
– @trychroma for Vector DB
– @huggingface Sentence Transformers for embeddings
– @AIatMeta `codellama-7b` for #LLM
– @LangChainAI for Integration
πΉοΈ App: https://t.co/ONOcMvy7dQ
π GH: https://t.co/Zur4uMXXMi https://t.co/zk0f3jYdyFRepoChat is an awesome @GitHub Repo chatbot built with @Streamlit
! – @trychroma for Vector DB
– @huggingface Sentence Transformers for embeddings
– @AIatMeta `codellama-7b` for #LLM
– @langchain for Integration App: https://
repochat.streamlit.app GH: https://
github.com/pnkvalavala/re
pochat
β¦ -
Neuralmagic Delivers Impressive Results in AI Optimization
By
–
Neuralmagic are doing an amazing job! Thanks for sharing this Derrick!
-
fastai Updates for PyTorch 2.1 Compatibility
By
–
Just pushed out a new version of fastai — now compatible with the recently-released @PyTorch version 2.1.
-
AI industry shifts toward closed source profit-driven projects
By
–
Not sure that'll happen — AFAICT it's largely moving to closed source secret projects now that are focused on making money, instead of creating things to benefit all society.
-
Larger proprietary models outperform open source alternatives
By
–
Ya, that's true. Plus larger models than the OSS models.
-
AI Safety and Knowledge Accessibility: Against Elitist AI Development
By
–
I am fully aligned with Yann LeCun's sentiment. There's a vast number of us committed to building AI that's both safe and beneficial, without resorting to needless alarmism. On top of this, I'm genuinely disturbed by the push to confine AI know-how to a selected few. Progress
-
Can Open Source Survive EU’s Cyber Resilience Act?
By
–
Can #opensource be saved from the EU's Cyber Resilience Act? https://
theregister.com/2023/10/13/can
_open_source_be_saved/
β¦ #EU #EuropeanUnion #RCE #ZeroTrust #ZeroDay #cybercrime #hacker #privacy #APT #bot #CISO #DDoS #hacking #phishing #CyberAttack #cybersecurity #Security #infosec #AppSec #CyberSec #databreach -
Small LLMs Poised to Outperform State-of-the-Art Models Soon
By
–
My bet is on 10-15b param (maybe even smaller) LLM models outperforming all state of the art soon. Everyone will be able to run them locally for free. WDYT?
-
vLLM Performance Comparison and Optimization Approaches
By
–
Thanks for sharing this. How does performance compare to vllm's approach? Can the two approaches be combined?