On emails: Have you tried training it on previous emails you've written/styles you want to replicate? I've noticed it can replicate the style of writing significantly better than GPT4
LLMS
-
Claude 3 Chat Memory Improves Conversation Personalization
By
–
Very interesting, I've also noticed that Claude 3 has a very good chat memory. The longer the conversation, the better and more personalized Claude becomes. Thanks for sharing!
-
Yi 34B Tech Report Reveals Model Architecture and Capabilities
By
–
Wondering what's powering the trending #yi34b? Curious about the tech behind it? At @01AI_Yi
, we've written a tech report revealing the inside scoop on:
Base and chat models
200K long context model
Depth-upscaled model
Vision-language model
Enjoy! -
Faster Inference Engines Enable Real-Time Content Iteration in Software Development
By
–
Thanks to @freufreu for this fun demo showing that the advent of faster inference engines allows us to iterate on the entire content at every prompt during software development. https://
youtu.be/eR855VNPjhk -
Claude 3 Opus Generates Executable Workflows From English Instructions
By
–
We are using models to go from English instructions to fully running workflows (code). Claude3 opus has been doing great; less chatty, more precise. @Lutra_AI
-
Claude 3 vs GPT-4: Real Use Cases and Performance Comparison
By
–
Seeing an interesting sentiment switch on AI Twitter for Claude 3 > GPT-4. But beyond hype, I want to see real use cases. If you're using Claude, I would love to hear your use case and where you find it beats ChatGPT. Featuring best responses in my newsletter (525k subs)
-
Multilingual LLM Model Outperforms Google Gemma 2
By
–
Leading in the OpenLLM leaderboard across multiple languages including English, German, Spanish, French, Italian, Dutch, and Portuguese, our model achieves top scores when ranked against larger sized models such as Google’s Gemma 2. (2/3)
-
Stable LM 2 1.6B: State-of-the-art Small Language Model
By
–
We’ve published our technical report on Stable LM 2 1.6B; our state-of-the-art small language model trained on multilingual data. This in-depth study covers the training methods utilized for both the base and instruction-tuned versions of the model. (1/3)
-
Daily Deep Learning Workout: CNNs, RNNs, and CUDA Kernel Training
By
–
daily deep learning workout: train two CNNs and three RNNs. perform ten minutes of quantized LLM transformer inference. write CUDA kernels until failure
-
Yi Open Foundation Models by 01.AI: Advanced Deep Learning
By
–
Yi: Open Foundation Models by 01 . AI Young et al.: https://
arxiv.org/abs/2403.04652 #ArtificialIntelligence #DeepLearning #MachineLearning