Build a powerful RAG pipeline with our latest blog, guiding you through leveraging LlamaIndex and Claude 3. Discover how to integrate LLMs for retrieval augmented generation with detailed insights. https://lnkd.in/gus-XHmT
Weights & Biases
Software Development
San Francisco, California 71,448 followers
The AI developer platform.
About us
Weights & Biases: the AI developer platform. Build better models faster, fine-tune LLMs, develop GenAI applications with confidence, all in one system of record developers are excited to use. W&B Models is the MLOps solution used by foundation model builders and enterprises who are training, fine-tuning, and deploying models into production. W&B Weave is the LLMOps solution for software developers who want a lightweight but powerful toolset to help them track and evaluate LLM applications. Weights & Biases is trusted by over a 1,000 companies to productionize AI at scale including teams at OpenAI, Meta, NVIDIA, Cohere, Toyota, Square, Salesforce, and Microsoft. Sign up for a 30-day free trial today at http://wandb.me/trial.
- Website
-
https://wandb.ai/site
External link for Weights & Biases
- Industry
- Software Development
- Company size
- 201-500 employees
- Headquarters
- San Francisco, California
- Type
- Privately Held
- Founded
- 2017
- Specialties
- deep learning, developer tools, machine learning, MLOps, GenAI, LLMOps, large language models, and llms
Products
Weights & Biases
Machine Learning Software
Weights & Biases helps AI developers build better models faster. Quickly track experiments, version and iterate on datasets, evaluate model performance, reproduce models, and manage your ML workflows end-to-end.
Locations
-
Primary
400 Alabama St
San Francisco, California 94110, US
Employees at Weights & Biases
Updates
-
Weights & Biases reposted this
📣 I am happy to announce that Weights & Biases Weave is now integrated with DSPy. It’s important to store traces of LLM applications in a central location, both during development and production. These traces can be useful for debugging and as a dataset to help you improve your application. 🧶 Weave will automatically capture traces for DSPy. To start tracking, call `weave.init()` and use the library as normal. 👉 Learn more at https://lnkd.in/gFaJZjyj
-
-
Join Weights & Biases’ Thomas Capelle and Mistral AI’s Sophia Yang, Ph.D. on July 17 at 8am PT / 5pm CEST for a webinar on reducing hallucinations in MistralAI models using out-of-domain data and W&B Weave. Register now: https://lnkd.in/gJjNh7VN
-
-
Don't miss our upcoming webinar, "Aligning Your LLM Judge with LlamaIndex and W&B Weave," on July 10 at 9 AM PDT. Ayush Thakur from Weights & Biases and Jerry Liu from LlamaIndex will explore effective evaluation strategies and best practices for aligning your LLM Judge. Register today to secure your spot: https://lu.ma/dywrdye5
-
-
Cisco’s Maryam Tabatabaeian shared how they revolutionized data tracking using Weights & Biases at #FullyConnected2024. Learn how comprehensive data versioning and an end-to-end pipeline create an efficient and collaborative environment. Watch the full video here: https://lnkd.in/gAuy6YV4
-
Announcing our new GenAI course: "Developer's Guide to LLM Prompting" ✔️Understand basic and advanced prompting techniques and when to use them ✔️Create consistent, reproducible outputs ✔️Customize LLMs for your use cases Featuring insights on LLMs in production from experts Anish Shah (W&B) and Teodora Danilovic (AutogenAI) Enroll now: https://lnkd.in/gTDfJsNi
-
-
Learn how to harness Retrieval-Augmented Generation (RAG) with Llama 3. Build a RAG system, set up the model, and monitor performance using Weights & Biases. Read more: https://lnkd.in/gayw2haX
-
-
Join Teodora Danilovic, a full-time prompt engineer, as she shares insights into the professional prompt creation process. Discover key considerations for using LLMs in production and success criteria for developing LLM applications for clients. Pre-register here: https://lnkd.in/gTDfJsNi
-
-
Weights & Biases reposted this
As part of building our support bot we needed a reliable LLM as a judge Earlier this year Ramanathan Parameshwaran & Ayush Thakur managed to get our judge to a good place after looking through initial the evals from the judge, making corrections to the prompt and adding few shot examples. With a reliable LLM as a judge we can test new ideas against our evals and update the bot's pipeline rapidly. Full details in our blog here https://lnkd.in/euwV73Pw Judge's prompt: https://lnkd.in/eZT3EiFR
-
-
Weights & Biases reposted this
New Webinar 🚨: A Principled Approach to RAG Experimentation + Evaluation 🧪 After 1+ years of RAG development, proper evaluation is still hard. We’re excited to partner with Weights & Biases on a webinar showing you how to build, evaluate, and iterate on a RAG pipeline. Jerry Liu, Ayush Thakur, and more will highlight different evaluation strategies with an LLM Judge against a RAG pipeline. W&B Weave is a new toolkit that gives you a comprehensive way to track and evaluate LLM applications, with features like comparisons, annotations, tracing, and more. Happening next Wednesday 7/10, 9am PT: https://lu.ma/dywrdye5
-