DeepSeek-R1-Distill
DeepSeek-R1-Distill is a family of six open-weight reasoning language models released by DeepSeek on January 20, 2025, alongside the flagship DeepSeek-R1 reasoning model.
Large Language Models
Explore language models, how they work, and the techniques used to build applications with them.
Explore articles
Browse subtopics: Training & Optimization
Articles that also belong to these categories. Counts cover all of Large Language Models.
All articles (545)AI Models (184)Open Source AI (165)Chinese AI (92)Natural Language Processing (58)AI Companies (53)Machine Learning (49)Mixture of Experts (46)Multimodal AI (41)Reasoning Models (39)Artificial Intelligence (37)OpenAI (35)AI Benchmarks (33)Anthropic (31)Google DeepMind (26)AI Agents (22)AI Safety (21)Developer Tools (20)Meta AI (20)AI Code Generation (18)Small Language Models (18)Training & Optimization (18)AI Inference (16)Model Architecture (14)Generative AI (13)NVIDIA (13)Prompt Engineering (13)AI Research (12)Deep Learning (12)Google (12)Model Evaluation (12)Data & Datasets (11)AI Tools & Products (9)Conversational AI (9)Microsoft (9)Transformer Models (9)AI Infrastructure (7)Diffusion Models (7)AI Alignment (5)Enterprise AI (5)Research Organizations (5)AI Hardware (4)Healthcare AI (4)Information Retrieval (4)Interpretability (4)People (4)Mathematics (3)AI History (2)AI for Science (2)Algorithms (2)Computer Vision (2)Legal AI (2)Reinforcement Learning (2)Speech & Audio AI (2)AI Policy (1)AI Policy & Regulation (1)AI in Cybersecurity (1)AI in Gaming (1)Autonomous Vehicles (1)ChatGPT (1)China AI (1)Drug Discovery (1)Neural Networks (1)Robotics (1)Software Development (1)Video Generation (1)
Showing 1-18 of 18 articles
InstructGPT
InstructGPT is a family of language models released by OpenAI in January 2022 that take the base GPT-3 and fine-tune it to follow user instructions more helpfully, truthfully, and with less toxic output, using…
LoftQ
LoftQ (short for LoRA-Fine-Tuning-aware Quantization) is a quantization and initialization framework for large language models that jointly quantizes a pre-trained backbone and initializes the attached…
LongLoRA
LongLoRA is a parameter-efficient fine-tuning technique that extends the context window of pre-trained large language models with substantially lower computation than full fine-tuning.
Multi-token prediction
Multi-token prediction (often abbreviated MTP) is a language modeling training objective in which the model is trained to predict several future tokens at each context position rather than only the next token.
Next-token prediction
Next-token prediction is the training objective used by most modern language models: the model reads a prefix of tokenized text, outputs a probability distribution over which token comes next, and training…
ORPO
ORPO (Odds Ratio Preference Optimization) is a preference alignment algorithm for large language models that merges supervised fine-tuning and preference alignment into a single training stage, eliminating the…
PiSSA
PiSSA (Principal Singular values and Singular vectors Adaptation) is a parameter-efficient fine-tuning method for large language models that initializes LoRA-style low-rank adapter matrices from the dominant…
Pipeline Parallelism
Pipeline parallelism (often abbreviated PP) is a distributed training strategy that splits the layers of a deep neural network across multiple accelerator devices so that each device holds one contiguous block…
QLoRA
QLoRA (Quantized Low-Rank Adaptation) is a parameter-efficient fine-tuning method that finetunes a 65-billion-parameter large language model on a single 48 GB GPU while matching the quality of full 16-bit…
SPIN (Self-Play Fine-Tuning)
SPIN (Self-Play fIne-tuNing) is a post-training method for large language models introduced by researchers at the University of California, Los Angeles (UCLA) in January 2024.
Self-Instruct
Self-Instruct is a semi-automated framework for aligning a pretrained large language model with instruction-following behavior by bootstrapping its training data from the model itself, introduced in December…
Self-Rewarding Language Models
Self-Rewarding Language Models (SRLM) is an iterative alignment method in which a single large language model alternately plays the role of policy (generating candidate responses to user prompts) and reward…
SimPO
SimPO (Simple Preference Optimization) is a reference-free offline preference learning algorithm for aligning large language models with human preferences.
Tensor Parallelism
Tensor parallelism (TP) is a distributed training technique that splits the individual weight matrices of a neural network layer across multiple devices, so that each device computes a partial result that is…
VeRA (Vector-based Random Matrix Adaptation)
Vector-based Random Matrix Adaptation (VeRA) is a parameter-efficient fine-tuning (PEFT) method for adapting large pretrained neural networks to downstream tasks while training only a tiny fraction of the…
WRAP (Web Rephrase Augmented Pre-training)
WRAP (Web Rephrase Augmented Pre-training) is a synthetic-data pre-training method introduced in the paper "Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling," posted to arXiv on 29…
rsLoRA (Rank-Stabilized LoRA)
rsLoRA (rank-stabilized LoRA) is a one-line modification to the low-rank adaptation fine-tuning method for large neural networks.