HuggingFace's 🍷 FineWeb Dataset, NVIDIA's Autoguidance, Snowflake’s Polaris Catalog, Jina Embeddings v2 on JumpStart, Nixtla’s StatsForecast 1.7.5

Microsoft’s Aurora, Skywork-MoE, Anthropic’s Claude 3 Opus on Vertex AI, HippoRAG, SymbCoT, Flash Attention, Applied LLM Quantisation Sagemaker

👋 Hello,

Welcome to DataPro#97—Your Essential Update on Data Science and ML! 

🧶 Top GitHub Repos 

• Buffer-of-Thought-LLM 

• FlagEmbedding 

• PyMC 

• Tablesaw 

• Spark-Alchemy 

• UltraMedical 

🧵 Industry Highlights 

• Build RAG applications using Jina Embeddings v2 on SageMaker JumpStart 

• Using Gemini in BigQuery for sentiment analysis 

• Anthropic’s Claude 3 Opus and tool use …