Pozify / src /pozify /slm

Commit History

  1. refactor: streamline evidence generation in coach summary; enhance JSON output contract and improve tokenization handling for local chat

    39810d5
  2. refactor: add functions for JSON payload extraction and validation in coach summary; streamline summary key handling and improve error reporting

    fbdb586
  3. refactor: introduce compact representation functions for metrics, issues, and knowledge cards; enhance summary evidence generation and improve error handling in JSON extraction

    7d8fed6
  4. refactor: enhance JSON response handling in coach summary generation; update response format instructions and improve error reporting for invalid JSON outputs

    1026352
  5. chore: remove Linux-specific dependencies from pyproject.toml and requirements.txt; update README to clarify usage of Nemotron implementation for local model inference

    b46e058
  6. chore: add ninja-build and build-essential to package requirements; update README and documentation to reflect changes in model configuration and local Transformers usage

    afa452e
  7. chore: update base model to NVIDIA-Nemotron-3-Nano-4B-BF16 across configurations and documentation; adjust max sequence length to 2048; upgrade GitHub Actions cache to v5

    ad20540

  1. feat: add support for local Transformers inference on Hugging Face Spaces with opt-in configuration

    NLag
    77c8c89
  2. docs: update default coach-summary model to build-small-hackathon/pozify-coach-summary1 and clarify fallback behavior in documentation

    5349353
  3. feat: add coach summary LoRA config and provider plumbing

    187ec78
  4. feat: expand coach retrieval with equipment and goal overlays

    19dfbdf
  5. feat(slm): add llama.cpp coach summary provider

    bb32784
  6. feat(coach): add local transformers provider

    02f8ffd

  1. Implement grounded coach summary with HF SLM

    f083cf4