OSS Hunt ๐ฑ๐ปDaily digs in open-source software! Curated gems, community insights, and tech trends. Built at @MistralAI Paris Hackathon by @CamelAIOrg๐ซ
Calling all AI enthusiasts, community builders, and tech advocates-become a ๐ซ CAMEL-AI Ambassador!
Do you love AI and multi-agent systems? Become a CAMEL-AI Ambassador and help build the future of AI.
What You Get:
โ Access to top AI research and resources
โ Meet AI experts and industry leaders
โ Get early updates on CAMELโs work
โ Be recognized in the AI community
โ Lead AI events, hackathons, and talks
What Youโll Do:
๐ Share news about CAMEL-AI and multi-agent systems
๐ Join or host AI talks, events, and hackathons
๐ Connect with AI communities online and offline
๐ Work with other ambassadors to grow the CAMEL network
Ready to make an impact?
Apply now! ๐ https://t.co/igZADWEUiK
#AI #MultiAgentSystems #CAMELAI
๐ข We've just added the Workforce module in the ๐ซ CAMEL framework!
Workforce is a system where multiple agents work together to solve tasks. ๐ค๐ค๐ค
Workforce follows a hierarchical architecture. A workforce can consist of multiple worker nodes, and each of the worker nodes will contain one agent or multiple agents as the worker.
The worker nodes are managed by a coordinator agent inside the workforce, and the coordinator agent will assign tasks to the worker nodes according to the description of the worker nodes, along with their tool sets. โ๏ธ
Alongside the coordinator agent, there is also a task planner agent inside the workforce. The task planner agent will take the responsibility of decomposing and composing tasks, so that the workforce can solve the task step by step. ๐ค
In the example bellow, you can use how a workforce works together to with agents that have different tools to plan a trip to Paris.
See the example ๐https://t.co/eOzd95oJw3
Thanks to our contributors @Whale__Eye & yiyiyi0817 for this significant update. ๐ค Explore more here: https://t.co/IGNOUoo5Do
Find out more about Workforce in our docs: https://t.co/L26LLCpQ9c
Introducing ๐ฆ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents
๐ฆ CRAB provides an end-to-end and easy-to-use framework to build multimodal agents, operate environments, and create benchmarks to evaluate them, featuring three key components:
- ๐ Cross-environment support - agents can operate tasks in ๐ฑ Android and ๐ป Ubuntu.
- ๐ธ๏ธ Graph evaluator - provides a fine-grain evaluation metric for agents.
- ๐ค Task generation - composes subtasks to automatically generate tasks.
By connecting all devices to agents, ๐ฆCRAB unlocks greater capabilities for human-like tasks than ever before.
Use ๐ฆ CRAB to benchmark your multimodal agents!
- ๐จโ๐ป Check out the repository: https://t.co/Pd5RorPaJi
- ๐ Read the paper: https://t.co/TvD2Q1QMvD
- ๐ Find out more via the project page: https://t.co/61BF1Pr4Jv
- ๐ซ Join our community: https://t.co/24hdnhI1Mi
Exciting updates in mistralai/mistral-inference! ย โจ The latest pull request brings LoRA support for improved adaptability. ย โฐ Check out the changes and big thanks to our contributors! #mistralai#mistralinference#updates
Exciting updates in mistralai/mistral-inference! โ Weve added LoRA to fine-tune embedding models, boosting the efficiency of large models. Kudos to our contributors! Learn more with this helpful tutorial. #MistralAI#LoRA#MachineLearning#AI#FineTuning#EmbeddingModels
Recent updates in mistralai/mistral-inference include the addition of LoRA, a technique for fine-tuning large language models. Thank you to the contributors for their hard work and dedication! #mistralai#mistralinference#LoRA#fine-tuning #nlp