Skip to content

@schneiderkamplab schneiderkamplab

Change the repository type filter

All

    Repositories list

    22 repositories

    • OLMo

      Public
      Modeling, training, eval, and inference code for OLMo
      Python
      •
      Apache License 2.0
      •450•0•0•0•Updated Oct 6, 2024Oct 6, 2024

    • aimrun

      Public
      simple interface for integrating aim into MLOps frameworks
      Python
      •
      MIT License
      •0•0•0•0•Updated Oct 5, 2024Oct 5, 2024

    • bitlinear

      Public
      BitLinear implementation
      Python
      •
      MIT License
      •5•18•0•1•Updated Oct 5, 2024Oct 5, 2024

    • diffusers

      Public
      🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
      Python
      •
      Apache License 2.0
      •5.3k•0•0•0•Updated Oct 1, 2024Oct 1, 2024

    • organoids

      Public
      Automatic segmentation and analysis of organoids
      Python
      •
      MIT License
      •0•0•0•0•Updated Sep 19, 2024Sep 19, 2024

    • syntheval

      Public
      Software for evaluating the quality of synthetic data compared with real data.
      benchmarkingtabular-datasynthetic-dataevaluating
      Python
      •
      MIT License
      •3•8•0•0•Updated Sep 17, 2024Sep 17, 2024

    • dolma

      Public
      Data and tools for generating and inspecting OLMo pre-training data.
      Python
      •
      Apache License 2.0
      •105•0•0•0•Updated Sep 3, 2024Sep 3, 2024

    • nanoT5

      Public
      Fast & Simple repository for pre-training and fine-tuning T5-style models
      Python
      •
      Apache License 2.0
      •72•1•0•2•Updated Aug 28, 2024Aug 28, 2024

    • synthesizers

      Public
      meta library for synthetic data generation
      Python
      •
      MIT License
      •0•2•0•0•Updated Aug 4, 2024Aug 4, 2024

    • aim

      Public
      Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.
      Python
      •
      Apache License 2.0
      •316•0•0•0•Updated Aug 3, 2024Aug 3, 2024

    • cramming

      Public
      Cramming the training of a (BERT-type) language model into limited compute.
      Python
      •
      MIT License
      •100•0•0•0•Updated Jul 4, 2024Jul 4, 2024

    • syntheval-model-benchmark-example

      Public
      Research paper supplement and code example of using SynthEval for executing a model benchmark
      Jupyter Notebook
      •
      MIT License
      •0•0•0•0•Updated Jun 10, 2024Jun 10, 2024

    • snopt

      Public
      Sorting Network OPTimizer
      Python
      •0•0•0•0•Updated Apr 27, 2024Apr 27, 2024

    • interviewbot

      Public
      A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
      Python
      •
      GNU Affero General Public License v3.0
      •5.2k•0•0•0•Updated Apr 12, 2024Apr 12, 2024

    • nanoGPT

      Public
      The simplest, fastest repository for training/finetuning medium-sized GPTs.
      Python
      •
      MIT License
      •5.8k•0•0•0•Updated Mar 24, 2024Mar 24, 2024

    • subprocessing

      Public
      A subprocess-based reimplementation of parts of Python's multiprocessing library
      Python
      •
      MIT License
      •0•0•0•0•Updated Mar 2, 2024Mar 2, 2024

    • transformers

      Public
      🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
      Python
      •
      Apache License 2.0
      •27k•0•0•0•Updated Feb 2, 2024Feb 2, 2024

    • youtube-insights

      Public
      Simple script for downloading Youtube comments without using the Youtube API
      Python
      •
      MIT License
      •224•0•0•0•Updated Jan 10, 2024Jan 10, 2024

    • cair

      Public
      CAIR rubric for privacy metrics
      MIT License
      •0•1•0•0•Updated Jan 5, 2024Jan 5, 2024

    • scaling-sdg

      Public
      Scaling study of Synthetic Data Generation models and evaluations
      Python
      •0•0•0•0•Updated Dec 30, 2023Dec 30, 2023

    • Alpaca-CoT

      Public
      We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. Meanwhile, we created a new branch to build a Tabular LLM.（我们分别统一了丰富的IFT数据（如CoT数据）、多种训练效率方法以及多种LLMs，三个层面上的接口，打造方便研究人员上手的LLM-IFT研究和使用平台。我们欢迎开源爱好者在这个repo上发起任何有意义的pr，一起将尽可能多的LLM相关技术集成进来。
      Jupyter Notebook
      •
      Apache License 2.0
      •245•0•0•0•Updated Sep 21, 2023Sep 21, 2023

    • detect-gpt

      Public
      DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature
      Python
      •
      MIT License
      •51•0•0•0•Updated May 11, 2023May 11, 2023