Uploaded August 2024 | Updated September 2026, 2 weeks ago
In this video, you will learn about Arcee Agent, a new state-of-the-art 7-billion parameter model created by Arcee.ai from Qwen2-7B. At the time of recording, Arcee Agent is one of the top models for function calls and tool usage, outperforming GPT-3.5 and current versions of GPT-4o.
Arcee Agent was built on Arcee Cloud and you can learn more at arcee.ai/product/arceecloud.
Here, I run the full precision model on my M3 MacBook and ollama to build a financial agent able to invoke the Yahoo Finance API to answer questions on listed companies: what's the stock price? Who's the CEO? What is this company doing? and more.
Along the way, I also show you that you don't need Github Copilot to explain code and generate documentation. You can use Arcee-Spark locally instead!
* Blog post: blog.arcee.ai/introducing-arcee-agent-a-specialized-7b-language-model-for-function-calling-and-tool-use-2
* Model page: huggingface.co/arcee-ai/Arcee-Agent
* Notebook: gitlab.com/juliensimon/arcee-demos/-/blob/main/arcee-agent/yahoo_finance_assistant.ipynb
⭐️⭐️⭐️ Don't forget to subscribe to be notified of future videos. Follow me on Medium at julsimon.medium.com or Substack at https://julsimon.substack.com. ⭐️⭐️⭐️
00:00 Introduction
00:44 Introducing Arcee-Agent
01:55 Running Arcee-Agent locally with ollama
03:00 Looking at the four functions implemented by our financial agent
06:50 Routing user queries to the appropriate function
08:25 Explaining and documenting our code with Arcee-Spark
10:02 Running inference with our financial agent
Configuration file for ollama:
FROM ./llama-spark-dpo-v0.3-Q5_K_S.gguf
#SmallLanguageModels #Arcee #HuggingFace #MachineLearning #DeepLearning #AI #opensource
Sign up for Arcee Cloud at https://www.arcee.ai, and please follow Arcee.ai on LinkedIn to stay on top of the latest Small Language Model action! linkedin.com/company/99895334
In this video, you will learn about Arcee Agent, a new state-of-the-art 7-billion parameter model created by Arcee.ai from Qwen2-7B. At the time of recording, Arcee Agent is one of the top models for function calls and tool usage, outperforming GPT-3.5 and current versions of GPT-4o.
Arcee Agent was built on Arcee Cloud and you can learn more at arcee.ai/product/arceecloud.
Here, I run the full precision model on my M3 MacBook and ollama to build a financial agent able to invoke the Yahoo Finance API to answer questions on listed companies: what's the stock price? Who's the CEO? What is this company doing? and more.
Along the way, I also show you that you don't need Github Copilot to explain code and generate documentation. You can use Arcee-Spark locally instead!
* Blog post: blog.arcee.ai/introducing-arcee-agent-a-specialized-7b-language-model-for-function-calling-and-tool-use-2
* Model page: huggingface.co/arcee-ai/Arcee-Agent
* Notebook: gitlab.com/juliensimon/arcee-demos/-/blob/main/arcee-agent/yahoo_finance_assistant.ipynb
⭐️⭐️⭐️ Don't forget to subscribe to be notified of future videos. Follow me on Medium at julsimon.medium.com or Substack at https://julsimon.substack.com. ⭐️⭐️⭐️
00:00 Introduction
00:44 Introducing Arcee-Agent
01:55 Running Arcee-Agent locally with ollama
03:00 Looking at the four functions implemented by our financial agent
06:50 Routing user queries to the appropriate function
08:25 Explaining and documenting our code with Arcee-Spark
10:02 Running inference with our financial agent
Configuration file for ollama:
FROM ./llama-spark-dpo-v0.3-Q5_K_S.gguf
#SmallLanguageModels #Arcee #HuggingFace #MachineLearning #DeepLearning #AI #opensource
Sign up for Arcee Cloud at https://www.arcee.ai, and please follow Arcee.ai on LinkedIn to stay on top of the latest Small Language Model action! linkedin.com/company/99895334
