in the API, GPT-4o is half the price AND twice as fast as GPT-4-turbo. and 5x rate limits.
LLMS
-
New AI Model Shows Promise During Testing Phase
By
–
it is a very good model (we had a little fun with the name while testing)
-
Explanation of AI Voice Mode Multimodal Reasoning
By
–
Voice mode being explained
— 🚨 AI News | TestingCatalog (@testingcatalog) 13 mai 2024
– reasoning across voice text and vision pic.twitter.com/hRifcUJwtLVoice mode being explained – reasoning across voice text and vision
-
OpenAI Releases GPT-4 Omni with Multimodal Capabilities
By
–
OpenAI just released GPT-4 Omni GPT-4o is the next-gen AI model in the GPT series that will bring GPT-4 level intelligence to everyone including the FREE users. GPT-4o reasons across voice, text and vision at the same time. Plus, a desktop version of ChatGPT.
-
GPT-4o: New Frontier Model Performance on LMSys Arena
By
–
GPT-4o is our new state-of-the-art frontier model. We’ve been testing a version on the LMSys arena as im-also-a-good-gpt2-chatbot . Here’s how it’s been doing.
-
Multimodal Search and RAG with Contrastive Learning
By
–
New short course: Building Multimodal Search and RAG", by @weaviate_io's @sebawita.
— Andrew Ng (@AndrewYNg) 13 mai 2024
Contrastive learning is used to train models to map vectors into an embedding space by pulling similar concepts closer together and pushing dissimilar concepts away from each other. This… pic.twitter.com/pUl3SXdOQGNew short course: Building Multimodal Search and RAG", by @weaviate_io
's @sebawita
. Contrastive learning is used to train models to map vectors into an embedding space by pulling similar concepts closer together and pushing dissimilar concepts away from each other. This -
Hugging Face Transformers Update and AI Agent Guide
By
–
Accessible on Hugging Face Transformers `main` branch (v4.41.0 lands this week) If you've never played with Agents, the following guide gets you up to speed as to what's possible with them.
-
Agents 2.0 Framework Released with High Performance Benchmarks
By
–
Agents 2.0 is out, and it's already the best-performing framework using an open model 🙌
— m_ric (@AymericRoucher) 13 mai 2024
✨ Simpler: prompt, tools, and attributes are accessible
🧩 Modular: use any LLM. Llama-3-70B-Instruct is 🔥
💪 Performant w/ React Agents
Top 1 of open models on GAIA, top 4 overall. pic.twitter.com/pzbVmuXysMAgents 2.0 is out, and it's already the best-performing framework using an open model Simpler: prompt, tools, and attributes are accessible Modular: use any LLM. Llama-3-70B-Instruct is Performant w/ React Agents Top 1 of open models on GAIA, top 4 overall.
-
Qwen1.5-110B-T Large Language Model Now Available on Poe
By
–
Qwen1.5-110B-T is hosted by @togethercompute
, and is available at https://
poe.com/Qwen-1.5-110B-T and on all Poe apps. (2/2)
