LogoLogo
Continuum WebsiteContinuum ApplicationsContinuum KnowledgeAxolotl Platform
Continuum Knowledge
Continuum Knowledge
  • Continuum
  • Data
    • Datasets
      • Pre Training Data
      • Types of Fine Tuning
      • Self Instruct Paper
      • Self-Alignment with Instruction Backtranslation
      • Systematic Evaluation of Instruction-Tuned Large Language Models on Open Datasets
      • Instruction Tuning
      • Instruction Fine Tuning - Alpagasus
      • Less is More For Alignment
      • Enhanced Supervised Fine Tuning
      • Visualising Data using t-SNE
      • UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
      • Training and Evaluation Datasets
      • What is perplexity?
  • MODELS
    • Foundation Models
      • The leaderboard
      • Foundation Models
      • LLama 2 - Analysis
      • Analysis of Llama 3
      • Llama 3.1 series
      • Google Gemini 1.5
      • Platypus: Quick, Cheap, and Powerful Refinement of LLMs
      • Mixtral of Experts
      • Mixture-of-Agents (MoA)
      • Phi 1.5
        • Refining the Art of AI Training: A Deep Dive into Phi 1.5's Innovative Approach
      • Phi 2.0
      • Phi-3 Technical Report
  • Training
    • The Fine Tuning Process
      • Why fine tune?
        • Does Fine-Tuning LLMs on New Knowledge Encourage Hallucinations?
        • Explanations in Fine Tuning
      • Tokenization
        • Tokenization Is More Than Compression
        • Tokenization - SentencePiece
        • Tokenization explore
        • Tokenizer Choice For LLM Training: Negligible or Crucial?
        • Getting the most out of your tokenizer for pre-training and domain adaptation
        • TokenMonster
      • Parameter Efficient Fine Tuning
        • P-Tuning
          • The Power of Scale for Parameter-Efficient Prompt Tuning
        • Prefix-Tuning: Optimizing Continuous Prompts for Generation
        • Harnessing the Power of PEFT: A Smarter Approach to Fine-tuning Pre-trained Models
        • What is Low-Rank Adaptation (LoRA) - explained by the inventor
        • Low Rank Adaptation (Lora)
        • Practical Tips for Fine-tuning LMs Using LoRA (Low-Rank Adaptation)
        • QLORA: Efficient Finetuning of Quantized LLMs
        • Bits and Bytes
        • The Magic behind Qlora
        • Practical Guide to LoRA: Tips and Tricks for Effective Model Adaptation
        • The quantization constant
        • QLORA: Efficient Finetuning of Quantized Language Models
        • QLORA and Fine-Tuning of Quantized Language Models (LMs)
        • ReLoRA: High-Rank Training Through Low-Rank Updates
        • SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models
        • GaLora: Memory-Efficient LLM Training by Gradient Low-Rank Projection
      • Hyperparameters
        • Batch Size
        • Padding Tokens
        • Mixed precision training
        • FP8 Formats for Deep Learning
        • Floating Point Numbers
        • Batch Size and Model loss
        • Batch Normalisation
        • Rethinking Learning Rate Tuning in the Era of Language Models
        • Sample Packing
        • Gradient accumulation
        • A process for choosing the learning rate
        • Learning Rate Scheduler
        • Checkpoints
        • A Survey on Efficient Training of Transformers
        • Sequence Length Warmup
        • Understanding Training vs. Evaluation Data Splits
        • Cross-entropy loss
        • Weight Decay
        • Optimiser
        • Caching
      • Training Processes
        • Extending the context window
        • PyTorch Fully Sharded Data Parallel (FSDP)
        • Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation
        • YaRN: Efficient Context Window Extension of Large Language Models
        • Sliding Window Attention
        • LongRoPE
        • Reinforcement Learning
        • An introduction to reinforcement learning
        • Reinforcement Learning from Human Feedback (RLHF)
        • Direct Preference Optimization: Your Language Model is Secretly a Reward Model
  • INFERENCE
    • Why is inference important?
      • Grouped Query Attention
      • Key Value Cache
      • Flash Attention
      • Flash Attention 2
      • StreamingLLM
      • Paged Attention and vLLM
      • TensorRT-LLM
      • Torchscript
      • NVIDIA L40S GPU
      • Triton Inference Server - Introduction
      • Triton Inference Server
      • FiDO: Fusion-in-Decoder optimised for stronger performance and faster inference
      • Is PUE a useful measure of data centre performance?
      • SLORA
  • KNOWLEDGE
    • Vector Databases
      • A Comprehensive Survey on Vector Databases
      • Vector database management systems: Fundamental concepts, use-cases, and current challenges
      • Using the Output Embedding to Improve Language Models
      • Decoding Sentence-BERT
      • ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT
      • SimCSE: Simple Contrastive Learning of Sentence Embeddings
      • Questions Are All You Need to Train a Dense Passage Retriever
      • Improving Text Embeddings with Large Language Models
      • Massive Text Embedding Benchmark
      • RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking
      • LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
      • Embedding and Fine-Tuning in Neural Language Models
      • Embedding Model Construction
      • Demystifying Embedding Spaces using Large Language Models
      • Fine-Tuning Llama for Multi-Stage Text Retrieval
      • Large Language Model Based Text Augmentation Enhanced Personality Detection Model
      • One Embedder, Any Task: Instruction-Finetuned Text Embeddings
      • Vector Databases are not the only solution
      • Knowledge Graphs
        • Harnessing Knowledge Graphs to Elevate AI: A Technical Exploration
        • Unifying Large Language Models and Knowledge Graphs: A Roadmap
      • Approximate Nearest Neighbor (ANN)
      • High Dimensional Data
      • Principal Component Analysis (PCA)
      • Vector Similarity Search - HNSW
      • FAISS (Facebook AI Similarity Search)
      • Unsupervised Dense Retrievers
    • Retrieval Augmented Generation
      • Retrieval-Augmented Generation for Large Language Models: A Survey
      • Fine-Tuning or Retrieval?
      • Revolutionising Information Retrieval: The Power of RAG in Language Models
      • A Survey on Retrieval-Augmented Text Generation
      • REALM: Retrieval-Augmented Language Model Pre-Training
      • Retrieve Anything To Augment Large Language Models
      • Generate Rather Than Retrieve: Large Language Models Are Strong Context Generators
      • Active Retrieval Augmented Generation
      • DSPy: LM Assertions: Enhancing Language Model Pipelines with Computational Constraints
      • DSPy: Compiling Declarative Language Model Calls
      • DSPy: In-Context Learning for Extreme Multi-Label Classification
      • Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programs
      • HYDE: Revolutionising Search with Hypothetical Document Embeddings
      • Enhancing Recommender Systems with Large Language Model Reasoning Graphs
      • Retrieval Augmented Generation (RAG) versus fine tuning
      • RAFT: Adapting Language Model to Domain Specific RAG
      • Summarisation Methods and RAG
      • Lessons Learned on LLM RAG Solutions
      • Stanford: Retrieval Augmented Language Models
      • Overview of RAG Approaches with Vector Databases
      • Mastering Chunking in Retrieval-Augmented Generation (RAG) Systems
    • Semantic Routing
    • Resource Description Framework (RDF)
  • AGENTS
    • What is agency?
      • Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves
      • Types of Agents
      • The risk of AI agency
      • Understanding Personality in Large Language Models: A New Frontier in AI Psychology
      • AI Agents - Reasoning, Planning, and Tool Calling
      • Personality and Brand
      • Agent Interaction via APIs
      • Bridging Minds and Machines: The Legacy of Newell, Shaw, and Simon
      • A Survey on Language Model based Autonomous Agents
      • Large Language Models as Agents
      • AI Reasoning: A Deep Dive into Chain-of-Thought Prompting
      • Enhancing AI Reasoning with Self-Taught Reasoner (STaR)
      • Exploring the Frontier of AI: The "Tree of Thoughts" Framework
      • Toolformer: Revolutionising Language Models with API Integration - An Analysis
      • TaskMatrix.AI: Bridging Foundational AI Models with Specialised Systems for Enhanced Task Completion
      • Unleashing the Power of LLMs in API Integration: The Rise of Gorilla
      • Andrew Ng's presentation on AI agents
      • Making AI accessible with Andrej Karpathy and Stephanie Zhan
  • Regulation and Ethics
    • Regulation and Ethics
      • Privacy
      • Detecting AI Generated content
      • Navigating the IP Maze in AI: The Convergence of Blockchain, Web 3.0, and LLMs
      • Adverse Reactions to generative AI
      • Navigating the Ethical Minefield: The Challenge of Security in Large Language Models
      • Navigating the Uncharted Waters: The Risks of Autonomous AI in Military Decision-Making
  • DISRUPTION
    • Data Architecture
      • What is a data pipeline?
      • What is Reverse ETL?
      • Unstructured Data and Generatve AI
      • Resource Description Framework (RDF)
      • Integrating generative AI with the Semantic Web
    • Search
      • BM25 - Search Engine Ranking Function
      • BERT as a reranking engine
      • BERT and Google
      • Generative Engine Optimisation (GEO)
      • Billion-scale similarity search with GPUs
      • FOLLOWIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions
      • Neural Collaborative Filtering
      • Federated Neural Collaborative Filtering
      • Latent Space versus Embedding Space
      • Improving Text Embeddings with Large Language Models
    • Recommendation Engines
      • On Interpretation and Measurement of Soft Attributes for Recommendation
      • A Survey on Large Language Models for Recommendation
      • Model driven recommendation systems
      • Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations
      • Foundation Models for Recommender Systems
      • Exploring the Impact of Large Language Models on Recommender Systems: An Extensive Review
      • AI driven recommendations - harming autonomy?
    • Logging
      • A Taxonomy of Anomalies in Log Data
      • Deeplog
      • LogBERT: Log Anomaly Detection via BERT
      • Experience Report: Deep Learning-based System Log Analysis for Anomaly Detection
      • Log-based Anomaly Detection with Deep Learning: How Far Are We?
      • Deep Learning for Anomaly Detection in Log Data: A Survey
      • LogGPT
      • Adaptive Semantic Gate Networks (ASGNet) for log-based anomaly diagnosis
  • Infrastructure
    • The modern data centre
      • Enhancing Data Centre Efficiency: Strategies to Improve PUE
      • TCO of NVIDIA GPUs and falling barriers to entry
      • Maximising GPU Utilisation with Kubernetes and NVIDIA GPU Operator
      • Data Centres
      • Liquid Cooling
    • Servers and Chips
      • The NVIDIA H100 GPU
      • NVIDIA H100 NVL
      • Lambda Hyperplane 8-H100
      • NVIDIA DGX Servers
      • NVIDIA DGX-2
      • NVIDIA DGX H-100 System
      • NVLink Switch
      • Tensor Cores
      • NVIDIA Grace Hopper Superchip
      • NVIDIA Grace CPU Superchip
      • NVIDIA GB200 NVL72
      • Hopper versus Blackwell
      • HGX: High-Performance GPU Platforms
      • ARM Chips
      • ARM versus x86
      • RISC versus CISC
      • Introduction to RISC-V
    • Networking and Connectivity
      • Infiniband versus Ethernet
      • NVIDIA Quantum InfiniBand
      • PCIe (Peripheral Component Interconnect Express)
      • NVIDIA ConnectX InfiniBand adapters
      • NVMe (Non-Volatile Memory Express)
      • NVMe over Fabrics (NVMe-oF)
      • NVIDIA Spectrum-X
      • NVIDIA GPUDirect
      • Evaluating Modern GPU Interconnect
      • Scalable Hierarchical Aggregation and Reduction Protocol (SHARP)
      • Next-generation networking in AI environments
      • NVIDIA Collective Communications Library (NCCL)
    • Data and Memory
      • NVIDIA BlueField Data Processing Units (DPUs)
      • Remote Direct Memory Access (RDMA)
      • High Bandwidth Memory (HBM3)
      • Flash Memory
      • Model Requirements
      • Calculating GPU memory for serving LLMs
      • Transformer training costs
      • GPU Performance Optimisation
    • Libraries and Complements
      • NVIDIA Base Command
      • NVIDIA AI Enterprise
      • CUDA - NVIDIA GTC 2024 presentation
      • RAPIDs
      • RAFT
    • Vast Data Platform
      • Vast Datastore
      • Vast Database
      • Vast Data Engine
      • DASE (Disaggregated and Shared Everything)
      • Dremio and VAST Data
    • Storage
      • WEKA: A High-Performance Storage Solution for AI Workloads
      • Introduction to NVIDIA GPUDirect Storage (GDS)
        • GDS cuFile API
      • NVIDIA Magnum IO GPUDirect Storage (GDS)
      • Vectors in Memory
Powered by GitBook
LogoLogo

Continuum - Accelerated Artificial Intelligence

  • Continuum Website
  • Axolotl Platform

Copyright Continuum Labs - 2023

On this page
  • Here's a step-by-step explanation
  • A more granular example
  • Prefix tuning has several advantages
  • Utility Benefits of Prefix Tuning
  • Experimental Proof

Was this helpful?

  1. Training
  2. The Fine Tuning Process
  3. Parameter Efficient Fine Tuning

Prefix-Tuning: Optimizing Continuous Prompts for Generation

PreviousThe Power of Scale for Parameter-Efficient Prompt TuningNextHarnessing the Power of PEFT: A Smarter Approach to Fine-tuning Pre-trained Models

Last updated 11 months ago

Was this helpful?

This highly cited January 2021 paper introduced a new technique for efficiently fine-tuning language models (LMs) called prefix-tuning.

This method addressed the challenges of efficiently adapting LMs to specific tasks while maintaining their generalisation capabilities and minimising the storage requirements for task-specific parameters.

Prefix tuning adapts pre-trained language models to specific tasks without modifying the original model's weights.

Prefix tuning draws inspiration from the concept of prompting, where task instructions and examples are prepended to the input to steer the LM's generation. However, instead of using discrete tokens, prefix tuning uses a continuous prefix vector.

Prefix-tuning involves prepending a sequence of continuous task-specific vectors, called a prefix, to the input of the LM.

The Transformer can attend to these prefix vectors as if they were a sequence of "virtual tokens". Unlike prompting, the prefix vectors do not correspond to real tokens but are learned during training.

Here's a step-by-step explanation

Soft Prompt Creation

  • In prefix tuning, we create a tensor called a "soft prompt" for each transformer block in the model.

  • This soft prompt is a set of learnable parameters that are specific to the task we want to adapt the model for.

Soft Prompt Processing

  • Before using the soft prompt, it is passed through a set of fully connected layers.

  • These layers transform the soft prompt into a suitable representation that can be combined with the main input to the transformer block.

Input Modification

  • The transformed soft prompt is then concatenated with the main input to the transformer block.

  • This concatenation happens along the sequence length dimension, meaning the soft prompt is added as additional tokens at the beginning of the input sequence.

Transformer Block Processing

  • The modified input, which now includes the soft prompt, is passed through the standard transformer block operations.

  • These operations include self-attention, layer normalisation, and feed-forward neural network layers, along with residual connections.

  • The transformer block processes the input as usual, but now it also takes into account the information provided by the soft prompt.

Training

  • During training, only the soft prompts are updated, while the pre-trained model's weights remain frozen.

  • The model learns to adapt to the specific task by adjusting the soft prompts based on the task-specific training data.

  • By keeping the original model's weights unchanged, prefix tuning allows for efficient adaptation without the need for fine-tuning the entire model.

The key idea behind prefix tuning is that by adding task-specific soft prompts to each transformer block, the model can learn to condition its behavior based on the prompts.

The soft prompts act as a "prefix" that guides the model's attention and computation towards the relevant information for the task at hand.

A more granular example

Define the prefix

  • The prefix is a sequence of continuous vectors that are prepended to the input sequence.

  • The length of the prefix is a hyperparameter that you can choose based on the complexity of the target personality and the available computational resources. Common prefix lengths range from 10 to 50 tokens.

  • The prefix is initialized as a trainable matrix PPP of size (prefixlength,embeddingdimension)(prefixlength, embeddingdimension)(prefixlength,embeddingdimension), where prefixlengthprefixlengthprefixlength is the number of prefix tokens and embeddingdimensionembeddingdimensionembeddingdimension is the size of the model's word embeddings.

  • Each row of the prefix matrix PPP corresponds to a prefix token, and the values in that row represent the embedding of that token.

  • The prefix matrix PPP is randomly initialised or initialised using the activations of real words that are relevant to the target personality. Initialising with relevant words can provide a good starting point for the prefix and potentially speed up convergence during training.

Modify the model architecture

  • In the Transformer architecture, the input sequence is typically represented as a matrix of word embeddings, where each row corresponds to a token in the sequence.

  • To incorporate the prefix, you concatenate the prefix matrix PPP with the input embeddings matrix along the sequence dimension (usually axis 1). This results in a new input matrix [P;X][P; X][P;X], where XXX is the original input embeddings matrix.

  • During the forward pass, the concatenated matrix [P;X] [P; X][P;X] is passed through the Transformer layers, which include self-attention and feed-forward layers.

  • The self-attention mechanism in the Transformer layers allows the prefix tokens to attend to and influence the representations of the input tokens, effectively steering the model's behavior.

  • Importantly, during training, only the prefix matrix PPP is updated, while the pre-trained model's parameters (i.e., the weight matrices in the Transformer layers) remain frozen. This ensures that the prefix adapts to the target personality while preserving the general language understanding captured by the pre-trained model.

Train the prefix

  • To train the prefix, you use a prepared dataset that consists of input-output pairs, where the input is a prompt or context and the output is the corresponding response that reflects the desired personality.

  • During training, you feed the input sequence through the modified model architecture, which includes the prefix matrix PPP concatenated with the input embeddings.

  • The model generates a probability distribution over the vocabulary for each position in the output sequence, and you compute a language modeling loss (e.g., cross-entropy loss) between the predicted probabilities and the true output tokens.

  • The gradients of the loss with respect to the prefix matrix PPP are computed using backpropagation, and the prefix matrix is updated using an optimisation algorithm like Adam.

  • The pre-trained model's parameters remain fixed during training, so only the prefix matrix PPP is updated to minimise the language modeling loss.

  • You can experiment with different hyperparameters such as the learning rate, batch size, and number of training epochs to find the optimal configuration that achieves the best performance on a validation set.

By training the prefix matrix PPP while keeping the pre-trained model's parameters frozen, you allow the prefix to adapt to the target personality while leveraging the general language understanding captured by the pre-trained model.

The prefix acts as a "soft prompt" that steers the model's behavior towards generating responses that align with the desired personality.

Prefix tuning has several advantages

  • It allows for efficient adaptation of pre-trained models to new tasks without modifying the original model's weights.

  • It requires fewer trainable parameters compared to fine-tuning the entire model, making it more computationally efficient.

  • It can be applied to any pre-trained transformer-based model without the need for task-specific architectures.

The diagram below demonstrates:

Utility Benefits of Prefix Tuning

Prefix-tuning allows for the independent training of tasks, enabling scalable personalisation without data cross-contamination.

Each user's data can be isolated, and a personalised prefix can be trained for each user, ensuring privacy and modularity. The independence of tasks also enables efficient batching across users and the creation of ensembles of multiple prefixes trained on the same task.

Experimental Proof

The paper demonstrates the effectiveness of prefix-tuning through extensive experiments on various natural language generation tasks, such as table-to-text generation and summarisation.

The results show that prefix-tuning outperforms other lightweight fine-tuning methods, such as adapter-tuning, while using substantially fewer parameters. It achieves performance comparable to full fine-tuning, especially in low-data regimes and when generalising to unseen topics.

The authors also explore the impact of prefix length on the model's performance, revealing that there is an optimal prefix length for each task.

Increasing the prefix length up to a certain threshold improves performance, but further increases lead to diminishing returns and potential overfitting.

Furthermore, the paper compares prefix-tuning with an embedding-only approach, where only the embeddings of the virtual tokens are optimised.

The results demonstrate that the embedding-only approach lacks the expressiveness necessary to achieve optimal performance, highlighting the importance of optimising the prefix vectors across all layers of the LM.

The discussion section of the paper emphasises the potential of prefix-tuning for real-world applications, particularly in scenarios requiring personalisation, privacy, efficiency, and scalability.

The modularity and independence of tasks make prefix-tuning suitable for enterprise-level applications where customer-specific interactions and computational efficiency are crucial.

In conclusion, the paper introduces a powerful and efficient method for fine-tuning large language models. By optimising continuous prompts in the form of prefix vectors, prefix-tuning achieves strong performance while significantly reducing the storage requirements for task-specific adaptations.

The technique's modularity, privacy-preserving nature, and scalability make it particularly suitable for real-world applications and enterprise-level deployments.

LogoPrefix-Tuning: Optimizing Continuous Prompts for GenerationarXiv.org
Prefix-Tuning: Optimising Continuous Prompts for Generation" by Xiang Li
A transformer block modified for prefix tuning
Page cover image