Weights & Biases

Calling all MCP developers!

We have a message for you right here. 👇

1 year ago | [YT] | 2

Weights & Biases

Focusing on what practical LLM tools can do for your business today, this talk will provide guidance on how every part of your business can become 10% more productive using LLMs. Highlights include:
- Practical Experience: Learn the latest prompting methodologies to get the outputs you need
- Introduction to EDD: Gain a solid understanding of Evaluation Driven Development principles and their necessity in AI application development.
- Real World Examples: Hear how Weights & Biases is using LLMs internally today to help grow our business efficiently
Check out Weave at wandb.me/weave

1 year ago | [YT] | 3

Weights & Biases

Weights & Biases has built the tools that helped OpenAI train GPT-4, and we recently released tools to help you leverage these tools for your own applications.

Join as Scott Condron discusses:
– Logging and versioning LLM interactions and surrounding data from development to production.
– Experimenting with prompting techniques, model changes, and parameters.
– Evaluating your models and measuring your progress.
-- Learn about the new toolkit, Weave, and how to use it to apply AI robustly.

1 year ago (edited) | [YT] | 3

Weights & Biases

Huge thanks to Microsoft Reactor team who co-hoster our latest event: Mastering MLOps w/ W&B + Microsoft's Phi-2: A Deep Dive into Advanced Language Models. Tune in and find out what W&B, Microsoft's Phi-2, GitOps and MLOps all have in common.

2 years ago | [YT] | 8

Weights & Biases

In the newest MLOps Community podcast, Demetrios Brinkmann hosted Anish Shah and Morgan McGuire where they shared insights on their journey into ML, the exciting work they're doing at Weights & Biases, and their thoughts on MLOps. They discuss using large language models (LLMs) for translation, pre-written code, and internal support. They discuss the challenges of integrating LLMs into products, the need for real use cases, and maintaining credibility.
Listen in to hear more about evaluating ML models collaboratively and the importance of continual improvement. Morgan and Anish also emphasize understanding retrieval and balancing novelty with precision. This episode provides a deep dive into Weights and Biases' work with LLMs and the future of ML evaluation in MLOps. It's a must-listen for anyone interested in LLMs and ML evaluation.

2 years ago | [YT] | 3

Weights & Biases

世界中の大企業や最先端AIスタートアップで、何十万ものML実践者が、高い水準のMLOpsおよびLLMopsを実現するためにWeights & Biases（WandB）を利用しています。この概要ビデオでは、MLワークフロー全体においてW&Bプラットフォームが記録システムとしてどのように機能し、生産性とコラボレーションを促進し、モデル評価とデプロイを容易にしてくれることをまとめました。

2 years ago | [YT] | 3

Weights & Biases

With artificial intelligence (AI) and large language models gaining popularity, ML developers need secure, scalable enterprise-ready tools that optimize developer productivity, streamline cross-functional collaboration, and enable model explainability. The W&B platform allows ML teams to build better models faster, track experimentation, improve collaboration across their organization, and implement automation.

2 years ago | [YT] | 7

Weights & Biases

In this session, hosted by DeepLearning.AI, on Fine-Tuning LLM Agents, you'll acquire crucial insights and techniques for enhancing the performance and specificity of local LLM Agents in application automation.

2 years ago | [YT] | 6

Weights & Biases

Check out our last week's session with @DataTalks.Club and Anish on LLM Agents!

2 years ago | [YT] | 2

Weights & Biases

"Data Cloud Now" anchor Ryan Green sat down with our Co-founder Chris Van Pelt, to discuss the impact gen AI and LLMs are having on W&B's business of helping companies develop high-quality ML results via tracking and monitoring evaluation tools.

2 years ago (edited) | [YT] | 1