Commit History

  1. Remove authentication for ungated Qwen model⁠

    Prashanth Ramakrishna
    5846074
  2. Force rebuild with Qwen2.5-7B⁠

    Prashanth Ramakrishna
    6d1a742
  3. Switch to Qwen2.5-7B-Instruct⁠

    Prashanth Ramakrishna
    296d6c6
  4. Switch to Mistral-7B-Instruct-v0.3⁠

    Prashanth Ramakrishna
    973b3fe
  5. Switch to Zephyr-7B-beta (truly ungated model)⁠

    Prashanth Ramakrishna
    f00bbe6
  6. Switch to Mistral-7B-Instruct-v0.1 (ungated model)⁠

    Prashanth Ramakrishna
    f9c7412
  7. Switch to Mistral-7B-Instruct-v0.3 for faster inference⁠

    Prashanth Ramakrishna
    40b044c

  1. Force rebuild - Deploy Qwen2.5-72B with 4xL4 tensor parallelism

    Prashanth Ramakrishna
    0a09fc5
  2. Switch to Qwen2.5-72B-Instruct with 4xL4 GPU tensor parallelism and NF4 quantization

    Prashanth Ramakrishna
    82e4ccc
  3. Fix TGI Numba caching issues - comprehensive environment setup

    Prashanth Ramakrishna
    ab82ad3
  4. Fix TGI Docker image - use v1.4 with Python dependencies

    Prashanth Ramakrishna
    457a3f0
  5. Replace Ollama with TGI for high-performance inference

    Prashanth Ramakrishna
    206ee47
  6. Revert to ENTRYPOINT and fix Ollama permissions with /tmp directory

    Prashanth Ramakrishna
    7d1b0bb
  7. Fix startup by using CMD instead of ENTRYPOINT for HF Spaces

    Prashanth Ramakrishna
    ad3212e
  8. Fix Ollama permissions by using /tmp directory

    Prashanth Ramakrishna
    d997b8f
  9. Fix entrypoint to ensure startup script executes

    Prashanth Ramakrishna
    a411574
  10. Initial deployment of Annotation Army Model Zoo with Ollama and multiple LLMs

    Prashanth Ramakrishna
    25eda95
  11. initial commit

    Verified signature
    8663ed0