That's great news! Have you tested it with peft *and* deepspeed zero3 together? If you, could you provide a complete example showing how to make that work?
CODE
-
Llama 2 LLMs Now Available on Databricks Marketplace
By
–
Llama 2 #GenAI models are now available on Databricks Marketplace! Enjoy access to Llama 2’s chat-oriented #LLMs with centralized governance and lineage tracking, easily usable through MLflow. Deploy it on LLM-optimized GPU endpoints in just one click
-
Free LLM Course: Zero-to-Hero Training and Fine-Tuning Guide
By
–
Super exciting news!! Along with @towards_AI
, @activeloop and @intel disruptor we just released our LLM free course, an attempt for a « zero-to-hero with LLMs » showing everything about LLMs (train, fine-tune, use RAG…) and the course is multi-modal! We have amazing articles, -
Fine-tuning Open-Source LLMs: Best Practices and Live Demo
By
–
When should you fine-tune an open-source LLM? and what's the best way to do it? Last chance to save your spot for our webinar this Thursday during which we'll cover all things fine-tuning including a live demo. Don't miss it! https://
pbase.ai/48KpA3H -
Spellburst: AI Tool Translates Ideas into Creative Code
By
–
How do you make art with code? Stanford scholars developed a new tool called Spellburst to make the process of translating ideas using natural language processing a seamless experience for creative coders.
-
Acquia Migrate Accelerate becomes open source
By
–
Start spreading the news! @acquia Migrate: Accelerate (created by the awesome @webchick
) is now open source! Thanks for the write-up, @wimleers https://
dev.acquia.com/blog/acquia-mi
grate-accelerate-now-open-source
… #drupal #opensource -
Symbolic Logic Integration in Knowledge Graphs and Neural Networks
By
–
There is active research on integrating symbolic logic into knowledge graphs / graph neural networks.
— AI (@DeepLearn007) 10 octobre 2023
My team and I did quite a bit of work on this 18 months ago integrating LLM models based on Transformers with Knowledge Graphs for logic and more explainable AI.
Here is a good… https://t.co/J7slPUa2k2There is active research on integrating symbolic logic into knowledge graphs / graph neural networks. My team and I did quite a bit of work on this 18 months ago integrating LLM models based on Transformers with Knowledge Graphs for logic and more explainable AI. Here is a good
-
Replit Code LLM Integration in Perplexity API
By
–
It was a pleasure working with @replit to integrate their most advanced code LLM replit-code-v1.5-3b to our API. Try it out through our pplx-api (https://t.co/SP03AxN18R) pic.twitter.com/6TZVFKbXDe
— Perplexity (@perplexity_ai) 10 octobre 2023It was a pleasure working with @replit to integrate their most advanced code LLM replit-code-v1.5-3b to our API. Try it out through our pplx-api (
http://
labs.pplx.ai/docs) -
LLMs Generate Synthetic Datasets Solving Data Labeling
By
–
Harnessing LLMs to Generate Synthetic Datasets In the context of machine learning, there's often a lack of labeled data or very little of it. This data collection and labeling process typically ends up taking a lot of effort and time. With the advent of LLMs, the paradigm
-
Databricks Repos Enhances Git Merge Rebase and Conflict Resolution
By
–
It doesn’t “Git” any easier than this 😉
— Databricks (@databricks) 9 octobre 2023
We're introducing new Git merge, Git rebase and conflict resolution features in Databricks Repos to make collaboration even more seamless.
See how ⬇️https://t.co/uVarsry69o pic.twitter.com/PAWeJAP26AIt doesn’t “Git” any easier than this We're introducing new Git merge, Git rebase and conflict resolution features in Databricks Repos to make collaboration even more seamless. See how https://
bit.ly/3PT4I2A