A user-friendly and efficient knowledge distillation framework for LLMs.
☆53Mar 16, 2026Updated this week
Alternatives and similar repositories for KDFlow
Users that are interested in KDFlow are comparing it to the libraries listed below
Sorting:
- An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset☆28Jan 19, 2025Updated last year
- MoE-Visualizer is a tool designed to visualize the selection of experts in Mixture-of-Experts (MoE) models.☆16Apr 8, 2025Updated 11 months ago
- ☆22Dec 11, 2024Updated last year
- [AAAI-2025] Towards Efficient and Intelligent Laser Weeding: Method and Dataset for Weed Stem Detection☆33May 15, 2025Updated 10 months ago
- A framework for few-shot evaluation of language models. including Turkish sets used in TurkishopenLLM leadboard on huggingface☆19Aug 30, 2024Updated last year
- ☆12Apr 18, 2023Updated 2 years ago
- TBD☆49Mar 13, 2026Updated last week
- ☆11Aug 14, 2024Updated last year
- UnOfficial Gradio Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Y…☆16Sep 30, 2024Updated last year
- Official repository for Activation-Informed Merging (AIM) of Large Language Models☆21Feb 10, 2025Updated last year
- GoLU, a novel, self-gated and element-wise activation function that performs well over a diverse set of tasks☆24Oct 4, 2025Updated 5 months ago
- ☆22Sep 10, 2024Updated last year
- ☆18Nov 20, 2024Updated last year
- Non-Autoregressive Math Word Problem Solver with Unified Tree Structure☆12Jan 13, 2024Updated 2 years ago
- This is for EMNLP 2024 Paper: AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction☆15Nov 4, 2024Updated last year
- Qualifying Exam Preparing☆17May 7, 2025Updated 10 months ago
- Implement Code for UniMix and Bayias Compensated Loss☆19Mar 7, 2023Updated 3 years ago
- [ECCV2022] Gumbel Optimised Loss for Long Tailed Instance Segmentation.☆18Nov 24, 2022Updated 3 years ago
- ☆27Sep 11, 2024Updated last year
- PyTorch implementation of EfficientNet☆10Sep 8, 2025Updated 6 months ago
- ☆15Mar 22, 2024Updated last year
- [NeurIPS 2024] VeLoRA : Memory Efficient Training using Rank-1 Sub-Token Projections☆21Oct 15, 2024Updated last year
- aigc evals☆10Dec 2, 2023Updated 2 years ago
- 'Phenesthe' (orig. φαίνεσθαι) is a system for the representation and processing of instantaneous and durative temporal phenomena.☆21Dec 3, 2024Updated last year
- Official implementation of paper "Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models"☆68Jan 13, 2026Updated 2 months ago
- An implementation of Wang et al.'s Signed Network Embedding in Social Media in PyTorch☆12Dec 24, 2017Updated 8 years ago
- ☆10May 9, 2016Updated 9 years ago
- A Unified Framework for Benchmarking Generative Electrocardiogram-Language Models (ELMs)☆42Feb 23, 2026Updated 3 weeks ago
- ☆15Jul 13, 2025Updated 8 months ago
- Data and Code for the paper "FinanceMath: Knowledge-Intensive Math Reasoning in Finance Domains"☆24Aug 10, 2024Updated last year
- Official code for the paper Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception. The code is based on t…☆19Aug 5, 2025Updated 7 months ago
- code for Preprint paper at Arxiv: MoT: Pre-thinking and Recalling Enable ChatGPT to Self-Improve with Memory-of-Thoughts☆24Nov 29, 2023Updated 2 years ago
- LLM reading group discussed at Houston Machine Learning Meetup☆35Nov 24, 2025Updated 3 months ago
- Implementation of the model: "Reka Core, Flash, and Edge: A Series of Powerful Multimodal Language Models" in PyTorch☆28Mar 9, 2026Updated last week
- This is a repository for "PMET: Precise Model Editing in a Transformer"☆55Sep 28, 2023Updated 2 years ago
- This is the repository for paper "CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models"☆30Oct 8, 2023Updated 2 years ago
- Agent framework for generating a synthetic dataset. This will be raw CoT and Reflection output to be cleaned up by a later step.☆15Apr 11, 2025Updated 11 months ago
- {DeepL, Google, WMT-Best, davinci-003, turbo, gpt-4} × {En-De, En-Cs, En-Ru, En-Zh, De-Fr, En-Ja, Uk-En, Uk-Cs, En-Hr, En-Ha, En-Is}☆14Jun 18, 2023Updated 2 years ago
- RENT (Reinforcement Learning via Entropy Minimization) is an unsupervised method for training reasoning LLMs.☆43Oct 31, 2025Updated 4 months ago