Skip to content
Change the repository type filter

All

    Repositories list

    • mergekit

      Public
      Tools for merging pretrained large language models.
      Python
      Other
      4995.2k18913Updated Feb 8, 2025Feb 8, 2025
    • spectrum

      Public
      for spectral randomness
      Python
      Apache License 2.0
      20000Updated Feb 6, 2025Feb 6, 2025
    • Developer resources to work with Arcee models on AWS
      Jupyter Notebook
      Apache License 2.0
      1800Updated Jan 30, 2025Jan 30, 2025
    • An Open Source Toolkit For LLM Distillation
      Python
      Apache License 2.0
      5247371Updated Jan 7, 2025Jan 7, 2025
    • Python
      0101Updated Dec 24, 2024Dec 24, 2024
    • entropix

      Public
      Entropy Based Sampling and Parallel CoT Decoding
      TypeScript
      Apache License 2.0
      320301Updated Dec 17, 2024Dec 17, 2024
    • Python
      Apache License 2.0
      314000Updated Dec 8, 2024Dec 8, 2024
    • fastmlx

      Public
      FastMLX is a high performance production ready API to host MLX models.
      Python
      Other
      30258172Updated Nov 29, 2024Nov 29, 2024
    • Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.
      TypeScript
      Other
      9.5k202Updated Nov 11, 2024Nov 11, 2024
    • DALM

      Public
      Domain Adapted Language Modeling Toolkit - E2E RAG
      Python
      Apache License 2.0
      4131365Updated Nov 8, 2024Nov 8, 2024
    • DAM

      Public
      Python
      74811Updated Nov 6, 2024Nov 6, 2024
    • optillm

      Public
      Optimizing inference proxy for LLMs
      Python
      Apache License 2.0
      157200Updated Nov 5, 2024Nov 5, 2024
    • Open-WebUI adaptation for Arcee model deployments
      Svelte
      MIT License
      8.4k002Updated Nov 5, 2024Nov 5, 2024
    • EvolKit

      Public
      EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language Models (LLMs).
      Jupyter Notebook
      MIT License
      2420002Updated Oct 30, 2024Oct 30, 2024
    • A framework for few-shot evaluation of language models.
      Python
      MIT License
      2.1k000Updated Oct 28, 2024Oct 28, 2024
    • Optimizing inference proxy for LLMs
      Python
      Apache License 2.0
      157000Updated Oct 25, 2024Oct 25, 2024
    • tau-bench

      Public
      Code and Data for Tau-Bench
      Python
      MIT License
      39000Updated Oct 22, 2024Oct 22, 2024
    • The Arcee client for executing domain-adpated language model routines https://pypi.org/project/arcee-py/
      Python
      52772Updated Oct 8, 2024Oct 8, 2024
    • Easy and lightning fast training of 🤗 Transformers on Habana Gaudi processor (HPU)
      Python
      Apache License 2.0
      227001Updated Sep 23, 2024Sep 23, 2024
    • Shell
      1000Updated Sep 10, 2024Sep 10, 2024
    • chat-ui

      Public
      TypeScript
      Apache License 2.0
      1.2k001Updated Aug 30, 2024Aug 30, 2024
    • vllm

      Public
      A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      Apache License 2.0
      5.6k001Updated Jul 31, 2024Jul 31, 2024
    • Ongoing research training transformer models at scale
      Python
      Other
      2.5k000Updated Jul 19, 2024Jul 19, 2024
    • axolotl

      Public
      Go ahead and axolotl questions
      Python
      Apache License 2.0
      945001Updated Jul 18, 2024Jul 18, 2024
    • The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
      Python
      Apache License 2.0
      125000Updated Jul 12, 2024Jul 12, 2024
    • domain adapted MOE training
      Python
      Other
      2.5k002Updated Jul 1, 2024Jul 1, 2024
    • A block pruning framework for LLMs.
      Python
      2100Updated Jun 20, 2024Jun 20, 2024
    • The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
      Python
      Apache License 2.0
      125100Updated May 24, 2024May 24, 2024
    • Python
      0500Updated May 6, 2024May 6, 2024
    • PruneMe

      Public
      Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models
      Python
      2621410Updated Apr 23, 2024Apr 23, 2024