LLMs
-
DiagrammerGPT generates better diagrams using LLMs
DiagrammerGPT is a new framework that uses large language models (LLMs) to generate…
-
Jina AI introduces world’s first open-source 8K text embedding model to rival OpenAI
Berlin-based AI company Jina AI has launched its second-generation text embedding model, jina-embeddings-v2.…
-
Introducing Lemur-70B and Lemur-70B-Chat: the open-source models harmonizing text and code for powerful language agents
Lemur and Lemur-Chat are openly accessible language models optimized for both natural language…
-
Multimodal foundation models: the future of AI assistants
Researchers from Google AI and Hugging Face present a comprehensive survey of multimodal…
-
Falcon 180B, the most powerful open-source large language model (LLM), is now available
The Technology Innovation Institute (TII) launched Falcon 180B, which is a scaled-up version of…
-
Recursive summarization: store and retrieve long-term dialogue memory in large language models
A new research paper suggests that large language models (LLMs) can be taught…
-
Meta’s SeamlessM4T can translate and transcribe speech and text across nearly 100 languages
Meta launched SeamlessM4T (Massively Multilingual & Multimodal Machine Translation), a new AI model…
-
AgentBench: a new tool to evaluate LLMs as agents in interactive environments
AgentBench is a multi-dimensional benchmark that tests how well Large Language Models (LLMs)…
-
How to train GPT-style models faster and cheaper with FlashAttention-2
FlashAttention-2 is a new method for attention computation in Transformers that outperforms the…
-
LeanDojo: a toolkit for developing and evaluating ReProver and other LLM-based theorem provers
LeanDojo is an open-source Lean playground that provides resources, data, models, and benchmarks for…