Attention Is All You Need
Paper
•
1706.03762
•
Published
•
41
Training & Architectures
Note 🔖 GPT-2: https://d4mucfpksywv.cloudfront.net/better-language-models/language_models_are_unsupervised_multitask_learners.pdf
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
Paper • 2307.08691 • Published • 7Note 🔖 GH: https://github.com/Dao-AILab/flash-attention 🔖 TGI Docs: https://huggingface.co/docs/text-generation-inference https://benjaminwarner.dev/2023/08/16/flash-attention-compile 🔖 Flash Attention-3: https://www.together.ai/blog/flashattention-3
-
Mixtral of Experts
Paper • 2401.04088 • Published • 157 -
Mistral 7B
Paper • 2310.06825 • Published • 47 -
Zephyr: Direct Distillation of LM Alignment
Paper • 2310.16944 • Published • 120 -
Llama 2: Open Foundation and Fine-Tuned Chat Models
Paper • 2307.09288 • Published • 239 -
Code Llama: Open Foundation Models for Code
Paper • 2308.12950 • Published • 22 -
Orca 2: Teaching Small Language Models How to Reason
Paper • 2311.11045 • Published • 70 -
OneLLM: One Framework to Align All Modalities with Language
Paper • 2312.03700 • Published • 20 -
WizardLM: Empowering Large Language Models to Follow Complex Instructions
Paper • 2304.12244 • Published • 13 -
The Falcon Series of Open Language Models
Paper • 2311.16867 • Published • 12 -
DocLLM: A layout-aware generative language model for multimodal document understanding
Paper • 2401.00908 • Published • 177
TeleChat Technical Report
Paper • 2401.03804 • Published • 7Note 🔖Dataset: https://huggingface.co/datasets/Tele-AI/TeleChat-PTD
-
TinyLlama: An Open-Source Small Language Model
Paper • 2401.02385 • Published • 88
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Paper • 2402.03300 • Published • 67Note Check their findings and reward models.
Foundation Models for Generalist Geospatial Artificial Intelligence
Paper • 2310.18660 • Published • 6
Chameleon: Mixed-Modal Early-Fusion Foundation Models
Paper • 2405.09818 • Published • 125Note 🔖Input: (Text, Image) Output: (Text, Image)
Gemini: A Family of Highly Capable Multimodal Models
Paper • 2312.11805 • Published • 45Note LATEST (Updated 2024): https://storage.googleapis.com/deepmind-media/gemini/gemini_1_report.pdf (Gemini 1.5): https://storage.googleapis.com/deepmind-media/gemini/gemini_v1_5_report.pdf OpenAI Stuff: 📜GPT-4V System Card: https://cdn.openai.com/papers/GPTV_System_Card.pdf 📜GPT 4: https://cdn.openai.com/papers/gpt-4-system-card.pdf Anthropic: 🔖Claude 3: https://www-cdn.anthropic.com/de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf
google/gemma-7b
Text Generation • Updated • 209k • • 3.02kNote 🔖 Series: https://huggingface.co/collections/google/gemma-release-65d5efbccdbb8c4202ec078b 🔖 Details: https://ai.google.dev/gemma/docs/model_card 🔖 Paper: https://storage.googleapis.com/deepmind-media/gemma/gemma-report.pdf
World Model on Million-Length Video And Language With RingAttention
Paper • 2402.08268 • Published • 36Note 🔖 https://largeworldmodel.github.io/ Context Scaling: 1M
-
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Paper • 2402.13753 • Published • 110 -
Gemini in Reasoning: Unveiling Commonsense in Multimodal Large Language Models
Paper • 2312.17661 • Published • 13 -
An In-depth Look at Gemini's Language Abilities
Paper • 2312.11444 • Published • 1
Question Aware Vision Transformer for Multimodal Reasoning
Paper • 2402.05472 • Published • 7Note Requires somewhat grounded data or product specific knowledge.
-
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Paper • 2312.00752 • Published • 138 -
Exponentially Faster Language Modelling
Paper • 2311.10770 • Published • 118 -
Training Transformers Together
Paper • 2207.03481 • Published • 4 -
Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws
Paper • 2401.00448 • Published • 27 -
FP8-LM: Training FP8 Large Language Models
Paper • 2310.18313 • Published • 31 -
Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
Paper • 2402.17177 • Published • 88 -
m-a-p/ChatMusician
Text Generation • Updated • 749 • 111 -
VisionLLaMA: A Unified LLaMA Interface for Vision Tasks
Paper • 2403.00522 • Published • 44 -
Training Compute-Optimal Large Language Models
Paper • 2203.15556 • Published • 10 -
Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?
Paper • 2207.10551 • Published -
Recurrent Linear Transformers
Paper • 2310.15719 • Published