Retrieval augmented generation is all the rage, but getting started can be overwhelming. To help you get started and navigate all of the moving pieces, we wrote a blog post about how to do RAG with @trychroma and @MistralAI
's 7B-instruct.
LLMS
-
Getting Started with RAG: Chroma and Mistral AI Guide
By
–
-
Free LLM Course: Training, Fine-tuning, and RAG Fundamentals
By
–
The LLM course is about showing everything about LLMs (train, fine-tune, use RAG…), and it is entirely free! If you want to learn how to train & fine-tune LLMs and have some Python skills, you should be ready to take the course. Start learning now: https://
learn.activeloop.ai/courses/llms/?
utm_source=social&utm_medium=youtube&utm_campaign=llmcourse
… -
Free LLM Course Series: Unlocking Language Models Full Potential
By
–
Good morning fellow AI enthusiast! This is the third video of my series for our free LLM course (details in)! In this one, we dive into unlocking the full potential of language models (and more)! Read more in this week's iteration: https://
open.substack.com/pub/louisbouch
ard/p/our-ai-tutor-is-live?r=25qlky&utm_campaign=post&utm_medium=web
… -
Jonathan McKinney to Present LangChain and Open Source LLMs at H2O Conference
By
–
Jonathan McKinney(
@pseudotensor
) http://
H2O.ai's Director of Research, will delve deep into Mastering #LangChain and Agents with Open Source #LLMs using h2oGPT at the upcoming #H2OGenAIWorld Conference Register for the event here: https://
h2o.ai/events/generat
ive-ai-summit/
… -
Baichuan Intelligent raises $300M from Alibaba, Tencent, Xiaomi
By
–
Baichuan Intelligent has raised $300 million in a Series A1 round led by Chinese tech giants Alibaba, Tencent, Xiaomi and several top investment institutions. Together with a previous $50 million angel round, Baichuan has now raised $350 million in total.
-
LLaMA-13B Model Classifies Text-to-Image Prompts for Safety
By
–
To go alongside sdxl-emoji I also trained a llama-13b fine-tune to classify text to image prompts as safe (0) or toxic (10). That model is also approaching 1M runs: https://
replicate.com/fofr/prompt-cl
assifier
… Trained on all the toxic prompts people tried after hitting #1 on Hacker News. -
Normcore LLM Reads: Practical Anti-Hype Reading List
By
–
Normcore LLM Reads https://
bit.ly/3KMZLFP Anti-hype LLM reading list
No hype and no vendor content if possible. Practical first-hand accounts and experience preferred. #AI #MachineLearning #DeepLearning #LLMs #DataScience -
LLMs Enable Easier Programming Language Creation and Adoption
By
–
On the other hand, it’s never been easier to build a new programming language and get adoption because of LLM’s. You can easily fine-tune a state of the art model to be amazing at using your new language.
-
Reverse Engineering ChatGPT Audio Conversation System Prompts
By
–
Has anyone dug out the system prompt/rules for the ChatGPT audio conversation mode?
-
ChatGPT-4 Alignment Challenges With Explicit User Constraints
By
–
In my experience, ChatGPT-4 exhibits an impressive ability to align with user intent. However, sometimes, when presented with explicit constraints (e.g. "use only the following characters: Arthur and his mom; DO NOT introduce any new characters"), the model seems to adhere to