On HumanEval and on MultiPL-E, Mistral Large 2 outperforms Llama 3.1 405B instruct, and scores just below GPT-4o. On MATH (0-shot, without CoT) it only falls behind GPT-4o.
(2/N)
CODE
-
Mistral Large 2 outperforms Llama 3.1 405B on coding benchmarks
By
–
-
Mistral Large 2: New 123B Model Outperforms Llama 3.1 405B
By
–
Today, we release Mistral Large 2, the new version of our largest model. Mistral Large 2 is a 123B-parameter model with a 128k context window. On many benchmarks (notably in code generation and math), it is superior or on par with Llama 3.1 405B. Like Mistral NeMo, it was trained
-
Flowise Cloud Launches Evaluations and LLM Performance Tracking
By
–
For Flowise Cloud, there are built-in Evaluations and Logging functionalities. Tokens, costs, and performance of LLMs can be traced, and also comes with versioning! Hop on to our waitlist https://
flowiseai.com/join! We're granting access to to users in batches starting today -
Hierarchical Multi-Agent Teams with Supervisor Architecture
By
–
7/7 Hierarchical Teams
— FlowiseAI (@FlowiseAI) 24 juillet 2024
Develop multiple agents from the ground up.
You can also create sub-teams with top-level supervisor, complemented by mid-level supervisors, forming a hierarchical multi agents! pic.twitter.com/lHpsC6EUSB7/7 Hierarchical Teams Develop multiple agents from the ground up. You can also create sub-teams with top-level supervisor, complemented by mid-level supervisors, forming a hierarchical multi agents!
-
Flowise 2.0 Agentic Workflow Templates Released
By
–
All the examples above are available as templates. These are just a few examples of what can be accomplished using this new agentic workflow approach. We're eager to see what you create with it! Release note: https://
github.com/FlowiseAI/Flow
ise/releases/tag/flowise2.0.0
… Docs: https://
docs.flowiseai.com/using-flowise/
agentflows
… -
Power of Building Apps with Open-Source Models Locally
By
–
This is real power, building apps with open-source models locally. Great share Akshay!
-
Diffusion Models Generate Code Non-Sequentially Like Impressive Breakthrough
By
–
Ver a una IA de forma autorregresiva generando código (secuencialmente, token tras token) ya era impresionante.
— Carlos Santana (@DotCSV) 24 juillet 2024
Pero ver métodos similares a los modelos de difusión generando trozos de código y llegando a una solución, además de impresionante ya me parece anti-intuitivo 😯 https://t.co/J3dFfUaP6pVer a una IA de forma autorregresiva generando código (secuencialmente, token tras token) ya era impresionante. Pero ver métodos similares a los modelos de difusión generando trozos de código y llegando a una solución, además de impresionante ya me parece anti-intuitivo
-
Celebrating open-source contributions to AI development
By
–
Thanks for all your work @Thom_Wolf
, open-source was a good bet! 🙂 -
Deploy Open Source LLMs as APIs with Ollama LMStudio
By
–
Prueba Ollama o LMStudio, te permite desplegar cualquier LLM open source como una API.
