Google’s update to Gemini 1.5 Pro gives the model ears. The model can now listen to uploaded audio files and churn out information from things like earnings calls or audio from videos without the need to refer to a written transcript.
During its Google Next event, Google also announced it’ll make Gemini 1.5 Pro available to the public for the first time through its platform to build AI applications, Vertex AI. Gemini 1.5 Pro was first announced in February. — Read More
Tag Archives: NLP
Meta confirms that its Llama 3 open source LLM is coming in the next month
At an event in London on Tuesday, Meta confirmed that it plans an initial release of Llama 3 — the next generation of its large language model used to power generative AI assistants — within the next month.
This confirms a report published on Monday by The Information that Meta was getting close to launch.
“Within the next month, actually less, hopefully in a very short period of time, we hope to start rolling out our new suite of next-generation foundation models, Llama 3,” said Nick Clegg, Meta’s president of global affairs. — Read More
Jamba: A Hybrid Transformer-Mamba Language Model
We present Jamba, a new base large language model based on a novel hybrid Transformer-Mamba mixture-of-experts (MoE) architecture. Specifically, Jamba interleaves blocks of Transformer and Mamba layers, enjoying the benefits of both model families. MoE is added in some of these layers to increase model capacity while keeping active parameter usage manageable. This flexible architecture allows resource- and objective-specific configurations. In the particular configuration we have implemented, we end up with a powerful model that fits in a single 80GB GPU. Built at large scale, Jamba provides high throughput and small memory footprint compared to vanilla Transformers, and at the same time state-of-the-art performance on standard language model benchmarks and long-context evaluations. Remarkably, the model presents strong results for up to 256K tokens context length. We study various architectural decisions, such as how to combine Transformer and Mamba layers, and how to mix experts, and show that some of them are crucial in large scale modeling. We also describe several interesting properties of these architectures which the training and evaluation of Jamba have revealed, and plan to release checkpoints from various ablation runs, to encourage further exploration of this novel architecture. We make the weights of our implementation of Jamba publicly available under a permissive license. — Read More
Large Language Models’ Emergent Abilities Are a Mirage
Two years ago, in a project called the Beyond the Imitation Game benchmark, or BIG-bench, 450 researchers compiled a list of 204 tasks designed to test the capabilities of large language models, which power chatbots like ChatGPT. On most tasks, performance improved predictably and smoothly as the models scaled up—the larger the model, the better it got. But with other tasks, the jump in ability wasn’t smooth. The performance remained near zero for a while, then performance jumped. Other studies found similar leaps in ability.
The authors described this as “breakthrough” behavior; other researchers have likened it to a phase transition in physics, like when liquid water freezes into ice. In a paper published in August 2022, researchers noted that these behaviors are not only surprising but unpredictable, and that they should inform the evolving conversations around AI safety, potential, and risk. They called the abilities “emergent,” a word that describes collective behaviors that only appear once a system reaches a high level of complexity. — Read More
RT-2: New model translates vision and language into action
Robotic Transformer 2 (RT-2) is a novel vision-language-action (VLA) model that learns from both web and robotics data, and translates this knowledge into generalised instructions for robotic control.
High-capacity vision-language models (VLMs) are trained on web-scale datasets, making these systems remarkably good at recognising visual or language patterns and operating across different languages. But for robots to achieve a similar level of competency, they would need to collect robot data, first-hand, across every object, environment, task, and situation.
In our paper, we introduce Robotic Transformer 2 (RT-2), a novel vision-language-action (VLA) model that learns from both web and robotics data, and translates this knowledge into generalised instructions for robotic control, while retaining web-scale capabilities. — Read More
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
We explore how generating a chain of thought — a series of intermediate reasoning steps — significantly improves the ability of large language models to perform complex reasoning. In particular, we show how such reasoning abilities emerge naturally in sufficiently large language models via a simple method called chain of thought prompting, where a few chain of thought demonstrations are provided as exemplars in prompting.
Experiments on three large language models show that chain of thought prompting improves performance on a range of arithmetic, commonsense, and symbolic reasoning tasks. The empirical gains can be striking. For instance, prompting a 540B-parameter language model with just eight chain of thought exemplars achieves state of the art accuracy on the GSM8K benchmark of math word problems, surpassing even finetuned GPT-3 with a verifier. — Read More
LoRA Land: Fine-Tuned Open-Source LLMs that Outperform GPT-4
We’re excited to release LoRA Land, a collection of 25 fine-tuned Mistral-7b models that consistently outperform base models by 70% and GPT-4 by 4-15%, depending on the task. LoRA Land’s 25 task-specialized large language models (LLMs) were all fine-tuned with Predibase for less than $8.00 each on average and are all served from a single A100 GPU using LoRAX, our open source framework that allows users to serve hundreds of adapter-based fine-tuned models on a single GPU. This collection of specialized fine-tuned models–all trained with the same base model–offers a blueprint for teams seeking to efficiently and cost-effectively deploy highly performant AI systems. — Read More
Latte: Latent Diffusion Transformer for Video Generation
We propose a novel Latent Diffusion Transformer, namely Latte, for video generation. Latte first extracts spatio-temporal tokens from input videos and then adopts a series of Transformer blocks to model video distribution in the latent space. In order to model a substantial number of tokens extracted from videos, four efficient variants are introduced from the perspective of decomposing the spatial and temporal dimensions of input videos. To improve the quality of generated videos, we determine the best practices of Latte through rigorous experimental analysis, including video clip patch embedding, model variants, timestep-class information injection, temporal positional embedding, and learning strategies. Our comprehensive evaluation demonstrates that Latte achieves state-of-the-art performance across four standard video generation datasets, i.e., FaceForensics, SkyTimelapse, UCF101, and Taichi-HD. In addition, we extend Latte to text-to-video generation (T2V) task, where Latte achieves comparable results compared to recent T2V models. We strongly believe that Latte provides valuable insights for future research on incorporating Transformers into diffusion models for video generation. — Read More
#nlp, #image-recognitionRetrieval-Augmented Generation for Large Language Models: A Survey
Large Language Models (LLMs) demonstrate significant capabilities but face challenges such as hallucination, outdated knowledge, and non-transparent, untraceable reasoning processes. Retrieval-Augmented Generation (RAG) has emerged as a promising solution by incorporating knowledge from external databases. This enhances the accuracy and credibility of the models, particularly for knowledge-intensive tasks, and allows for continuous knowledge updates and integration of domain-specific information. RAG synergistically merges LLMs’ intrinsic knowledge with the vast, dynamic repositories of external databases. This comprehensive review paper offers a detailed examination of the progression of RAG paradigms, encompassing the Naive RAG, the Advanced RAG, and the Modular RAG. It meticulously scrutinizes the tripartite foundation of RAG frameworks, which includes the retrieval , the generation and the augmentation techniques. The paper highlights the state-of-the-art technologies embedded in each of these critical components, providing a profound understanding of the advancements in RAG systems. Furthermore, this paper introduces the metrics and benchmarks for assessing RAG models, along with the most up-to-date evaluation framework. In conclusion, the paper delineates prospective avenues for research, including the identification of challenges, the expansion of multi-modalities, and the progression of the RAG infrastructure and its ecosystem. — Read More
Original Paper
Groq
Groq is on a mission to set the standard for GenAI inference speed, helping real-time AI applications come to life today. Using a new type of end-to-end processing unit system, called a LPU Inference Engine, with LPU standing for Language Processing Unit™, Groq provides the fastest inference for computationally intensive applications with a sequential component to them, such as AI language applications (LLMs). Groq supports standard machine learning (ML) frameworks such as PyTorch, TensorFlow, and ONNX for inference. Groq does not currently support ML training with the LPU Inference Engine. — Read More
#nlp, #nvidia
Rick's Cafe AI 