2. Configure the Embedchain App For this application we will use Llama-3, you can choose from OpenAI, cohere, anthropic or any other LLM of your choice. Select the vector database as the opensource chroma db (you are free to choose any other vector database of your choice).
LLMS
-
Building RAG Web Apps with Streamlit and Embedchain
By
–
1. Import necessary libraries • Streamlit for building the web app
• Embedchain for the RAG functionality
• tempfile for creating temporary files and directories -
Build Local LLM RAG App Chat PDF Llama-3
By
–
Build a LLM app with RAG to chat with PDF using Llama-3 running locally on your computer (100% free and without internet):
-
Thoughts on 8x22b Release Without 8x7b Model
By
–
its honestly a bit odd they uploaded 8x22b first without 8x7b. but surely it cant be far behind now esp if its really sparse upcycled (do we know for sure?)
-
Voice AI models and their impact on usage rate limits
By
–
The Plus rate limit cap will become much more relevant when a new voice model will drop. Voice conversations eat your quota super fast
-
SolarLLM Integration Tutorial Sharing on Google Colab
By
–
Love this. May I use #SolarLLM at https://
colab.research.google.com/drive/1hiGt4dB
WEZ8Xsb3fUtONg3EEbguumaZ0#scrollTo=IqM-T1RTzY6C
… and add it as a tutorial at https://
github.com/hunkim/SolarLL
MZeroToAll
…? I will include the original link and give credit. -
Solar-1-Mini-Chat-Ja: Fast Japanese LLM Outperforms GPT3.5
By
–
Please try `solar-1-mini-chat-ja`. It outperforms GPT3.5 and Rakuten LLM, a famous model in Japan, but it's 3x faster. You can use it right away at https://
console.upstage.ai -
Enterprise Alignment Matters More Than AI Superalignment
By
–
Worried about #ai #superalignment? Don't be.
— Snorkel AI (@SnorkelAI) 22 mai 2024
According to Snorkel AI CEO @ajratner , while superalignment is a worthy goal, worrying about it right now is akin to designing seat belts for flying saucers.
Instead, worry about enterprise alignment. #LLMs and #foundationmodels… pic.twitter.com/o4OKyBaACXWorried about #ai #superalignment? Don't be. According to Snorkel AI CEO @ajratner , while superalignment is a worthy goal, worrying about it right now is akin to designing seat belts for flying saucers. Instead, worry about enterprise alignment. #LLMs and #foundationmodels
-
Clarification on AI model voice capabilities
By
–
Nope, the model is still the same w/o new voice capabilities
-
Experimenting with Larger Prompts on Cheaper Models
By
–
Now we're talkin. 🙂 I have quite a few 1,000-4,000 token prompts currently in use. But aiming to experiment with running cheaper models with bigger prompts that essentially contain a ton of examples. Fine tune without the fine tune.