Skip to content
@LLM-OS-Models

LLM-OS-Models

README.md

LLM-OS-Models

LLM-OS-Models is an organization for building and evaluating model capabilities that make up an LLM operating-system stack.

Repository Map

  • docs: central documentation and experiment cards
  • llm-os-eval-core: shared evaluation schemas, runners, graders, and reporters
  • Terminal: terminal-agent training and Terminal-Bench evaluation
  • MD-Retrieval: Markdown retrieval and grounded answer evaluation
  • Tool-Call: tool-calling, schema validation, and execution evaluation
  • Text2SQL: document-grounded text-to-SQL evaluation and training
  • Coding-Agent: repo-grounded coding-agent evaluation and training
  • DocAI-OCR: OCR and structured document parsing for downstream agents
  • Deep-Research: research-agent evaluation and external comparison track

Common Comparison Tracks

  • T_base
  • T_sft
  • S_base
  • S_sft
  • S_kld

Popular repositories Loading

  1. Terminal Terminal Public

    https://huggingface.co/LLM-OS-Models

    Python 4

  2. KoHRM-text KoHRM-text Public

    Python 4

  3. docs docs Public

  4. .github .github Public

    Organization profile for LLM-OS-Models

  5. llm-os-eval-core llm-os-eval-core Public

    Shared evaluation core for LLM-OS-Models

    Python

  6. MD-Retrieval MD-Retrieval Public

    MD file retrieval and grounded answer evaluation

    Python

Repositories

Showing 10 of 11 repositories
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…