All tags
Person: "maximelabonne"
The Ultra-Scale Playbook: Training LLMs on GPU Clusters
deepseek-native-sparse-attention r1-1776 paligemma-2-mix muse baichuan-m1-14b stripedhyena-2 huggingface deepseek perplexity-ai google-deepmind microsoft baichuan stripedhyena gpu-training scaling multimodality vision model-training foundation-models medical-llm genome-modeling robotic-manipulation interactive-content eliebakouch nouamanetazi lvwerra thom-wolf proftomyeh alex-wang aravsrinivas _akhaliq _philschmid mervenoyann reach_vb arankomatsuzaki maximelabonne
Huggingface released "The Ultra-Scale Playbook: Training LLMs on GPU Clusters," an interactive blogpost based on 4000 scaling experiments on up to 512 GPUs, providing detailed insights into modern GPU training strategies. DeepSeek introduced the Native Sparse Attention (NSA) model, gaining significant community attention, while Perplexity AI launched R1-1776, an uncensored and unbiased version of DeepSeek's R1 model. Google DeepMind unveiled PaliGemma 2 Mix, a multi-task vision-language model available in 3B, 10B, and 28B sizes. Microsoft introduced Muse, a generative AI model trained on the game Bleeding Edge, and presented Magma, a foundation model for multimodal AI agents excelling in UI navigation and robotic manipulation. Baichuan-M1-14B was announced as a state-of-the-art medical LLM trained on 20T tokens, and a fully open-source 40B genome modeling model using StripedHyena 2 architecture was also released. "Making your own gaming experience is coming sooner than you'd think," noted in relation to Muse.
LLaDA: Large Language Diffusion Models
llada-8b llama-3-8b step-video-t2v-30b step-audio-chat-132b llama-2-7b stepfun-ai scale-ai cambridge llamaindex diffusion-models text-generation multimodality video-generation voice-processing benchmarking instruction-following model-scaling gpu-usage long-context multi-turn-dialogue arankomatsuzaki _akhaliq omarsar0 iscienceluvr gallabytes maximelabonne reach_vb
LLaDA (Large Language Diffusion Model) 8B is a breakthrough diffusion-based language model that rivals LLaMA 3 8B while training on 7x fewer tokens (2 trillion tokens) and using 0.13 million H800 GPU hours. It introduces a novel text generation approach by predicting uniformly masked tokens in a diffusion process, enabling multi-turn dialogue and instruction-following. Alongside, StepFun AI released two major models: Step-Video-T2V 30B, a text-to-video model generating up to 204 frames with high coherence and motion quality, and Step-Audio-Chat 132B, a voice-to-voice model. Additionally, challenging multimodal benchmarks like Scale AI's EnigmaEval and Cambridge's ZeroBench highlight current frontier models scoring zero, emphasizing the difficulty of these tasks. The community also noted the return of diffusion models in language modeling, a previously speculative architecture now scaled successfully.
not much happened today
gpt-4-0613 gpt-3.5-turbo-0613 gpt-4o-2024-08-06 mistral-large-2 gpt4-turbo claude-3-opus idefics3-llama bigllama-3.1-1t-instruct llama-3-120b-instruct openai mistral-ai meta-ai-fair structured-outputs function-calling json-schema benchmarking multimodality context-windows model-scaling ai-hardware vision speech-processing robotics ai-regulation sama rohanpaul_ai corbtt guillaumelample mervenoyann maximelabonne aidan_mclau adcock_brett ylecun
OpenAI introduced structured outputs in their API with a new "strict" mode and a "response_format" parameter, supporting models like gpt-4-0613, gpt-3.5-turbo-0613, and the new gpt-4o-2024-08-06. They also halved the price of gpt-4o to $2.50 per million tokens. Mistral Large 2 outperforms gpt4-turbo and claude-3-opus on hard benchmarks and coding tasks. Idefics3-Llama offers multimodal capabilities with a 10k token context window. BigLlama-3.1-1T-Instruct is an upscaled version of llama-3-120b-instruct. New benchmark "big_model_smell" measures creativity and reliability. Figure 02 robot features advanced AI hardware with onboard vision language model, enhanced battery, and speech-to-speech reasoning. Yann LeCun expressed concerns about California's SB1047 regulation.
Apple Intelligence Beta + Segment Anything Model 2
llama-3-405b llama-3 segment-anything-model meta-ai-fair apple image-segmentation memory-attention video-processing pretraining cloud-tpus post-training synthetic-data instruction-following reasoning writing benchmarking bindureddy maximelabonne reach_vb
Meta advanced its open source AI with a sequel to the Segment Anything Model, enhancing image segmentation with memory attention for video applications using minimal data and compute. Apple Intelligence delayed its official release to iOS 18.1 in October but launched developer previews on MacOS Sequoia, iOS 18, and iPadOS 18, accompanied by a detailed 47-page paper revealing extensive pretraining on 6.3T tokens and use of Cloud TPUs rather than Apple Silicon. The paper highlights improvements in instruction following, reasoning, and writing through post-training and synthetic data. Benchmarks show Apple’s model scores lower than Llama 3, but with trusted human evaluations. Additionally, Meta released Llama 3.1 with a 405B parameter model, marking a significant open-source frontier model release.
Cursor reaches >1000 tok/s finetuning Llama3-70b for fast file editing
gpt-4 gpt-4o gpt-4-turbo gpt-4o-mini llama bloom stable-diffusion cursor openai anthropic google-deepmind huggingface speculative-decoding code-edits multimodality image-generation streaming tool-use fine-tuning benchmarking mmlu model-performance evaluation synthetic-data context-windows sama abacaj imjaredz erhartford alexalbert svpino maximelabonne _philschmid
Cursor, an AI-native IDE, announced a speculative edits algorithm for code editing that surpasses GPT-4 and GPT-4o in accuracy and latency, achieving speeds of over 1000 tokens/s on a 70b model. OpenAI released GPT-4o with multimodal capabilities including audio, vision, and text, noted to be 2x faster and 50% cheaper than GPT-4 turbo, though with mixed coding performance. Anthropic introduced streaming, forced tool use, and vision features for developers. Google DeepMind unveiled Imagen Video and Gemini 1.5 Flash, a small model with a 1M-context window. HuggingFace is distributing $10M in free GPUs for open-source AI models like Llama, BLOOM, and Stable Diffusion. Evaluation insights highlight challenges with LLMs on novel problems and benchmark saturation, with new benchmarks like MMLU-Pro showing significant drops in top model performance.
DeepSeek-V2 beats Mixtral 8x22B with >160 experts at HALF the cost
deepseek-v2 llama-3-120b llama-3-400b gpt-4 mistral phi claude gemini mai-1 med-gemini deepseek-ai mistral-ai microsoft openai scale-ai tesla nvidia google-deepmind mixture-of-experts multi-head-attention model-inference benchmarking overfitting robotics teleoperation open-source multimodality hallucination-detection fine-tuning medical-ai model-training erhartford maximelabonne bindureddy adcock_brett drjimfan clementdelangue omarsar0 rohanpaul_ai
DeepSeek V2 introduces a new state-of-the-art MoE model with 236B parameters and a novel Multi-Head Latent Attention mechanism, achieving faster inference and surpassing GPT-4 on AlignBench. Llama 3 120B shows strong creative writing skills, while Microsoft is reportedly developing a 500B parameter LLM called MAI-1. Research from Scale AI highlights overfitting issues in models like Mistral and Phi, whereas GPT-4, Claude, Gemini, and Llama maintain benchmark robustness. In robotics, Tesla Optimus advances with superior data collection and teleoperation, LeRobot marks a move toward open-source robotics AI, and Nvidia's DrEureka automates robot skill training. Multimodal LLM hallucinations are surveyed with new mitigation strategies, and Google's Med-Gemini achieves SOTA on medical benchmarks with fine-tuned multimodal models.