News

User Story

Engineering

Culture

Artur Niederfahrenhorst

Kourosh Hakhamaneshi

Based on the popular “Needle In a Haystack” benchmark and RAG, we share our process of creating a problem-specific fine-tuning dataset to extend the context of models to build better RAG systems.

fine tuning llms query featured

Fine-tuning LLMs for longer context and better RAG systems

Rehaan Ahmad

In this blog, we compare full-parameter fine-tuning with LoRA and answer questions around the strengths and weaknesses of the two techniques. 

lora blog 1

Fine-Tuning LLMs: In-Depth Analysis with LLAMA-2 | Anyscale

Fine-Tuning LLMs: LoRA or Full-Parameter? An in-depth Analysis with Llama 2

We examine the Llama-2 models under 3 real-world use cases and show that fine-tuning yields significant accuracy improvements.

Llama 2 performance

Fine-Tuning Llama-2: Tailoring Models to Unique Applications

Fine-Tuning Llama-2: A Comprehensive Case Study for Tailoring Models to Unique Applications

Waleed Kadous

Fine tuning is one approach to domain-specific model refinement (DSMR), but it’s not a silver bullet for improving domain-specific performance.

fine-tune-img-1

Fine Tuning Is For Form, Not Facts | Anyscale

Fine tuning is for form, not facts

Avnish Narayan

Learn how you can achieve up to 1.7x infrastructure cost savings by using the newly introduced multi-GPU training stack in RLlib.

Figure 2. Episodic Return of PPO Agents trained using differing amounts of Nvidia T4 GPUs. Using more GPUs led to significantly higher performance in the same time-frame.


rllib_figure_5

RLlib Multi-GPU Stack | Affordable, Scalable RL Agents Training

Introducing RLlib Multi-GPU Stack for Cost Efficient, Scalable, Multi-GPU RL Agents Training

Ray Summit 2024, the annual Ray community conference, is back in San Francisco, CA this September 30th through October 2nd. It is a two-day event with a third day dedicated to training.

Call for Proposals is open Blog Post

Ray Summit 2024 Call for Proposals is now open

Intel and Anyscale have integrated Ray with Gaudi3. Gaudi3 is AI-optimized for efficient training and other machine learning workloads.

Anyscale - Intel

Accelerating AI: Harnessing Intel(R) Gaudi(R) 3 with Ray 2.10

Anyscale is teaming with NVIDIA to combine the developer productivity of Ray Serve and RayLLM with the cutting-edge optimizations from NVIDIA Triton Inference Server software and the NVIDIA TensorRT-LLM library.

NVIDIA-Anyscale Logo 1280x680.jpg

Low-latency Generative AI Model Serving with Ray, NVIDIA Triton Inference Server, and NVIDIA TensorRT-LLM

Generating embeddings is a critical task for developing successful RAG applications, and Anyscalew with Pinecone is the most cost-efficient solution for this workflow.

blog-anyscale-pincone

RAG at Scale: 10x Cheaper Embedding Computations with Anyscale and Pinecone

This section is used to order the "Types" and "Tags" that show up for filters on the Blog Index

Types

Products / Libraries

Blog

Hosted Anyscale is in Private Preview. Click here to request access!

Anyscale is the leading AI application platform. With Anyscale, developers can build, run and scale AI applications instantly.

Posts by Kourosh Hakhamaneshi

No posts found.