Kim Kuhlman, PhD’s Post

NVIDIA  released a new llama 3 finetune which is trained specifically for RAG tasks. It beats even gpt-4 on retrieval augmented generation oriented benchmarks. Even their 8B parameters model is almost as good as gpt-4. This is really good for basically everyone. As RAG is one of the most profitable applications of LLMs. https://lnkd.in/e728hc2T

Hey #devs, check out this technical blog for a new way to use NVIDIA's Nemotron-4 340B model for Synthetic Data Generation (SDG)! https://lnkd.in/gJaU-ivG #developer #learning #llm #gpt #mlops #syntheticdata #data #datascience #llmops #ai #ml #nemotron #nemo

NVIDIA Research has unveiled SteerLM, a new technique that allows users to customize the responses of large language models like Llama 2 during inference. SteerLM provides more control over model outputs by letting users define key attributes to steer the model's behavior. The new technique is shown to outperform models using supervised fine-tuning and reinforcement learning from human feedback. https://lnkd.in/ekgZ8nde

Announcing HelpSteer: An Open-Source Dataset for Building Helpful LLMs NVIDIA recently announced the NVIDIA NeMo SteerLM technique as part of the NVIDIA NeMo framework. This technique enables users to control large language model (LLM) responses during inference. The developer community has shown great interest in using the approach for building custom LLMs. The NVIDIA NeMo team is now open-sourcing a multi-attribute dataset called Helpfulness SteerLM dataset (HelpSteer). This new resource enables developers to get started with using the SteerLM technique quickly and build state-of-the-art custom models. HelpSteer is a collaborative effort between our team and Scale AI. Coupled with the SteerLM technique, it improves the factuality and coherence of responses. Developers can now guide LLM responses on additional attributes like complexity and verbosity and enhance the overall controllability of the responses for end-users. By using this new dataset and the SteerLM technique, NVIDIA trained a Llama 2 70B foundational model that outperforms the Llama 2-70B chat model on MT Bench and TruthfulQA MC2 benchmarks.

NVIDIA just released Nemotron-4, and it outperformed GPT-4. Key Highlights: ✅ The big unlock is the synthetic data generation, which mimicks real world data, and allows for training and fine tuning LLMs 🔓 Nemotron-4 democratizes LLM training, enabling organizations to rapidly develop custom language models tailored to their specific domains and use cases, without the high costs and challenges of acquiring extensive datasets. Read the announcement below #NVIDIA #SyntheticData #LLMs #GenerativeAI https://lnkd.in/eRVavfD7

Microsoft released BitNet b1.58, a new Large Language Model (LLM) using 1.58 bits per parameter, reducing computational demands significantly while maintaining performance. Unlike traditional 16-bit models, BitNet employs ternary values (-1, 0, 1), slashing GPU memory use and energy consumption by up to 3.5 times and 71 times respectively, without sacrificing model accuracy. BitNet b1.58 achieves comparable or superior results to FP16 models like LLaMA 3B in perplexity and various language tasks starting from a 3 billion parameter size. The reduction in precision to 1-bit minimizes the need for energy-heavy floating-point operations, particularly in matrix multiplication, speeding up computations and lowering energy costs. #llm #ai

🚀 Excited to share my latest project for the Generative AI Agents Developer Contest by NVIDIA and LangChain! 🌟 Introducing NVIDIA LangChain DocsAgent – an RAG agent that you can ask questions related to retrieved API and framework documentation. This tool is powered by NVIDIA's cutting-edge AI models and the LangChain🦜️🔗 framework and deployed with LangServe🦜️🏓 and LangSmith🦜🛠️ for chain trace monitoring. 📚🤖 🔍 Key Features: - Natural language querying of documentation - Efficient document retrieval and ranking - Customizable database creation with retrieved data 🔧 Built With: - NVIDIA NIM API (nv-rerank-qa-mistral-4b): Re-ranks retrieved documents based on relevance to the question. - NVIDIA NIM API (nvidia/embed-qa-4): Generates high-quality embeddings for documentation chunks for use in similarity searches. - NVIDIA NIM API (meta/llama3-70b): Provides the LLM that generates coherent responses. - langchain_nvidia_ai_endpoints: Integrates NVIDIA AI models with LangChain for embedding generation, document ranking, and LLM interactions. - LangChain: Core framework for building the RAG agent, facilitating smooth integration between document retrieval, prompt crafting, and response generation. - LangSmith: Provides advanced monitoring and analytics for tracing and debugging interactions within the RAG agent. - LangServe: Deploys and manages the agent as a web service, handling user queries and interacting with the Chroma database. GitHub repo: https://lnkd.in/gd7fjrKp 🎥 Check out this demo video to see the DocsAgent in action! #NVIDIADevContest #LangChain NVIDIA AI

Exa is building a tool that allows AI models to perform something like a web search, but with an AI-native twist. The cofounders bought a million dollars worth of GPUs (which were easier to get in those days) and, using a vector database and embeddings (not a classic transformer-based LLM), they began to build an machine learning model trained to natively understand links rather than words and sentences. #AI #Google #Exa #Nvidia #YCombinator #Lightspeed

🚀 Exciting News from NVIDIA: Introducing Nemotron-4 340B for Synthetic Data Generation! In the rapidly evolving landscape of AI, data quality and accessibility are pivotal. NVIDIA's latest Nemotron-4 340B models represent a breakthrough in Synthetic Data Generation (SDG), offering unparalleled capabilities to augment existing datasets and empower AI innovations. ##Features: 🔹 #Nemotron-4 340B Family: Includes Base, Instruct, and state-of-the-art Reward models. 🔹 #Open Model License: Permissive licensing for personal, research, and commercial use. 🔹 #SteerLM Reward Model: Leads in benchmark performance with a 92.0 overall score on Reward Bench. 🔹 HelpSteer2 Dataset: CC-BY-4.0 licensed, enhancing data diversity and quality. #Synthetic Data Generation (SDG) with Nemotron-4 340B: By leveraging the Instruct model for response generation and the Reward model for quality assessment, businesses can efficiently scale AI training datasets with minimal human annotation. This approach not only accelerates model development but also ensures high-quality outputs aligned with specific domain needs. #Case Study: NVIDIA's research demonstrates the effectiveness of SDG, achieving comparable results to traditionally trained models with just a fraction of human-annotated data. Join us in exploring the future of AI with Nemotron-4 340B models. Dive into our technical resources and model deployment guides to unleash the full potential of synthetic data in your AI initiatives. 🔗 Learn More: https://lnkd.in/d8KQXzph Try the model from here: https://lnkd.in/dv6AX2CQ

The AI product landscape is evolving fast, and it's tricky to keep up with all the commercial offerings, open source libraries and frameworks. TechNews attempted a top 100 indexing of specific products and technologies by ascending order of media interest. Let us know what we missed, so the next time we refresh this list we close any gaps. #artificialintelligence #opensource #frameworks #llms https://lnkd.in/gYdi3pYK