This repository presents AdaptiVocab, a vocabulary-centric method for adapting LLMs to domain-specific tasks. By modifying the tokenizer and embedding layers, AdaptiVocab reduces token usage by over 25% without compromising performance. The code includes modules for vocabulary optimization, embedding initialization, and lightweight fine-tuning.
☆10Dec 4, 2025Updated 11 months ago
Alternatives and similar repositories for AdaptiVocab
Users that are interested in AdaptiVocab are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆16Aug 7, 2026Updated 3 months ago
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆18Apr 30, 2025Updated last year
- A repository to get acquainted with basic training tasks in natural language processing and machine learning☆11Dec 27, 2023Updated 2 years ago
- Swap one RAG pipeline stage, hold the rest fixed, and measure whether the gain survives composition. The framework behind "Retrieval Augm…☆35Updated this week
- Adapt full attention LLM to sliding window attention☆14Feb 20, 2026Updated 8 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Agentic Claude Code skills for academic writing: review simulation, revision, and prose improvement.☆19Oct 22, 2026Updated 2 weeks ago
- 基于蓝图系统的人工神经网络可视化集成开发环境。化繁为简，简单拖拽，就能完成复杂的任务。☆10Aug 2, 2026Updated 3 months ago
- A react template based on the UI style of Arknights.☆11Apr 9, 2025Updated last year
- Mechanistic Interpretability on Reasoning using Gemma-Scope for BlueDot Impact Course.☆13Sep 27, 2024Updated 2 years ago
- 隐藏你B站顶部搜索框里那莫名其妙的推荐搜索☆10Nov 4, 2025Updated last year
- Bilibili的IndexTTs2的ComfyUI版本。自动下载模型，支持多人物对话，使用简单。☆13Dec 5, 2025Updated 11 months ago
- Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases☆11Jan 17, 2020Updated 6 years ago
- Context optimization for AI coding agents — lower token cost and latency without sacrificing accuracy.☆74Updated this week
- ☆20Jul 9, 2022Updated 4 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- NAACL 2025 main conference: "VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Te…☆13Apr 27, 2025Updated last year
- Speech emotion recognition using LSTM, SVM and MLP | 语音情感识别☆10Jul 1, 2019Updated 7 years ago
- Conditional computing research: hybrid approach for stacked MoE and Early-Exit Neural Networks☆14Jul 17, 2025Updated last year
- ☆17May 17, 2026Updated 5 months ago
- Optimize any AI agent’s skills, tools/MCP, and prompts against your own evals.☆69Updated this week
- Limited automatic tabular ML pipelines for generic MEDS datasets.☆21Updated this week
- A high-performance database and Python reader interface for MEDS datasets☆22Aug 12, 2026Updated 2 months ago
- ☆11May 2, 2019Updated 7 years ago
- Official PyTorch implementation for "TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors" [ACL 2026]☆49Apr 14, 2026Updated 6 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆14Jun 3, 2024Updated 2 years ago
- Federated Self-Training for Data-Efficient Audio Recognition☆10May 7, 2022Updated 4 years ago
- ☆14Mar 24, 2023Updated 3 years ago
- ☆29Jan 29, 2026Updated 9 months ago
- The official implementation of DMEL the method presented in the paper "DMEL: The differentiable log-Mel spectrogram as a trainable layer …☆24Dec 21, 2024Updated last year
- Python bindings for the Rust crate ignore☆13Oct 22, 2026Updated 2 weeks ago
- Light-weight transfer learning framework for on-device speech and audio recognition using pre-trained image convolutional neural networks…☆18Apr 16, 2022Updated 4 years ago
- ☆13Feb 3, 2025Updated last year
- Cross-platform file sharig application for desktop and mobile devices☆11May 2, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- python-to-triton-llm☆10Aug 25, 2025Updated last year
- 杀戮尖塔2正式版的godot源码☆34Apr 16, 2026Updated 6 months ago
- 2026 Advanced Photonics Nexus journal paper: "Efficient Gerchberg-Saxton algorithm deep unrolling for phase retrieval with a complex forw…☆19Mar 28, 2026Updated 7 months ago
- Code for the paper "FedFisher: Leveraging Fisher Information for One-Shot Federated Learning" by Divyansh Jhunjhunwala, Shiqiang Wang, an…☆14Feb 10, 2024Updated 2 years ago
- PHP with FPM Dockerfile for trusted automated Docker builds.☆12Mar 2, 2016Updated 10 years ago
- ☆19Oct 19, 2023Updated 3 years ago
- Code release of paper "ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning" (NeurIPS 2023)☆18Dec 30, 2023Updated 2 years ago
Are these results useful?