Mistral Agents
Mistral AI has improved model customization for its flagship models, introduced "Agents" for custom workflows, and released a stable SDK version, enhancing accessibility and effectiveness of generative AI for developers.
Read original article
Mistral AI has announced several advancements aimed at enhancing the development and sharing of generative AI applications. Key updates include improved model customization capabilities for their flagship models, such as Mistral Large 2 and Codestral. Developers can now customize these models using base prompts, few-shot prompting, or fine-tuning with their own datasets, ensuring high performance similar to the original models. This customization is expected to facilitate the integration of generative AI into various applications with specific domain knowledge and context. Additionally, Mistral AI introduced an alpha release of "Agents," which allows users to create custom behaviors and workflows by wrapping models with additional context and instructions. This feature is designed to enhance collaboration within organizations by enabling the sharing of complex workflows. Furthermore, the company has released a stable version of its client SDK, mistralai 1.0, which includes significant usability and consistency improvements for both Python and Typescript users. These updates reflect Mistral AI's commitment to making generative AI more accessible and effective for developers.
- Mistral AI enhances model customization for flagship models like Mistral Large 2.
- Developers can fine-tune models using their own datasets for specific applications.
- Introduction of "Agents" allows for custom workflows and behaviors in AI applications.
- A stable version of the mistralai SDK has been released, improving usability for developers.
- Mistral AI aims to facilitate the integration of generative AI into diverse applications.
Related
Codestral Mamba
Codestral Mamba, a new Mamba2 language model by Mistral AI, excels in code generation with linear time inference and infinite sequence modeling. It rivals transformer models, supports 256k tokens, and aids local code assistance. Deployable via mistral-inference SDK or TensorRT-LLM, it's open-source under Apache 2.0.
Mistral NeMo
Mistral AI introduces Mistral NeMo, a powerful 12B model developed with NVIDIA. It features a large context window, strong reasoning abilities, and FP8 inference support. Available under Apache 2.0 license for diverse applications.
Mathstral: 7B LLM designed for math reasoning and scientific discovery
MathΣtral, a new 7B model by Mistral AI, focuses on math reasoning and scientific discovery, inspired by Archimedes and Newton. It excels in STEM with high reasoning abilities, scoring 56.6% on MATH and 63.47% on MMLU. The model's release under Apache 2.0 license supports academic projects, showcasing performance/speed tradeoffs in specialized models. Further enhancements can be achieved through increased inference-time computation. Professor Paul Bourdon's curation of GRE Math Subject Test problems contributed to the model's evaluation. Instructions for model use and fine-tuning are available in the documentation hosted on HuggingFace.
Can the New Mathstral LLM Accurately Compare 9.11 and 9.9?
Mathstral is a new 7B model by Mistral AI for math reasoning, with a 32k context window and Apache 2.0 license. It aims to improve common sense in math problem-solving, deployable locally with LlamaEdge and shareable via GaiaNet for customization and integration.
Large Enough – Mistral AI
Mistral AI released Mistral Large 2, enhancing code generation, reasoning, and multilingual support with 123 billion parameters. It outperforms competitors and is available for research use via various cloud platforms.
11 commentsWhat's the difference from sending the system prompt in the api call, as usual?
Edit: Oh, missed that: "We’re working on connecting Agents to tools and data sources."
That's all you need from the model to be able to use it in an agent. Tell it to output commands in a given JSON format.
I assume that Mistral's API already allowed you to define the system prompt, right?
It's hard to read data with widespread anti-abuse checks (CAPTCHAs), lack of open-format data (RSS support being spotty), and restricted APIs (ex: Twitter API). Companies have all the incentives to prevent bot use, and select for human eyeballs.
If we had a Yahoo Pipes sort of golden age, GenAI agents would have a vaster playground to play in, and would be more useful for us.
Consider building an agent for choosing what to do on weekends for a group of friends. The agent would need to keep state for past activities (X, Y, and Z went upstate to Storm King last week) and users' preferences (ex: liking dosas or Calder, dietary restrictions). This part is easy enough - you could just keep a notebook that's passed as context. Older context gets simply deleted or condensed into high level points.
But would it be easy for the agent to:
1) Look up nearby restaurants and events? (Perhaps Resy/OpenTable allow listing restaurants, but it's likely they have tons of anti-abuse tech. Is there even a place where you could see a list of public events - Google pays a third-party for this feed.)
2) Actuate on behalf of the user? (Do Resy and OpenTable allow authority delegation so the agent could book restaurants for users? There's no standard way to do this across venue types - concerts, museums, cooking classes. Is it realistic for agents to click through these sites on their own?)
>We’re working on connecting Agents to tools and data sources... So tools and RAG for data sources aren't available yet.
Way behind GPTs/assistants. What's the point of this yet?
Related
Codestral Mamba
Codestral Mamba, a new Mamba2 language model by Mistral AI, excels in code generation with linear time inference and infinite sequence modeling. It rivals transformer models, supports 256k tokens, and aids local code assistance. Deployable via mistral-inference SDK or TensorRT-LLM, it's open-source under Apache 2.0.
Mistral NeMo
Mistral AI introduces Mistral NeMo, a powerful 12B model developed with NVIDIA. It features a large context window, strong reasoning abilities, and FP8 inference support. Available under Apache 2.0 license for diverse applications.
Mathstral: 7B LLM designed for math reasoning and scientific discovery
MathΣtral, a new 7B model by Mistral AI, focuses on math reasoning and scientific discovery, inspired by Archimedes and Newton. It excels in STEM with high reasoning abilities, scoring 56.6% on MATH and 63.47% on MMLU. The model's release under Apache 2.0 license supports academic projects, showcasing performance/speed tradeoffs in specialized models. Further enhancements can be achieved through increased inference-time computation. Professor Paul Bourdon's curation of GRE Math Subject Test problems contributed to the model's evaluation. Instructions for model use and fine-tuning are available in the documentation hosted on HuggingFace.
Can the New Mathstral LLM Accurately Compare 9.11 and 9.9?
Mathstral is a new 7B model by Mistral AI for math reasoning, with a 32k context window and Apache 2.0 license. It aims to improve common sense in math problem-solving, deployable locally with LlamaEdge and shareable via GaiaNet for customization and integration.
Large Enough – Mistral AI
Mistral AI released Mistral Large 2, enhancing code generation, reasoning, and multilingual support with 123 billion parameters. It outperforms competitors and is available for research use via various cloud platforms.