Hugging Face's logo

Spaces:
IDKHowToCodeFr
/
vera-engine
Running

App Files Community
vera-engine

Commit History

29 days ago

  1. Merge pull request #1 from i-win-again/main⁠

    Rachit Mangawa
    0cfbac9

24 days ago

  1. deleted bload and updated judge sim and gitignore

    IDKHowToCodeFr
    2dc82f8

  2. feat: implement 4-tier LLM fail-fast cascade & benchmark-based local 3B selection

    IDKHowToCodeFr
    6b1caf3

  3. new files

    IDKHowToCodeFr
    a38eb61

29 days ago

  1. deleted bload and updated judge sim and gitignore

    IDKHowToCodeFr
    aedf01f

30 days ago

  1. feat: implement 4-tier LLM fail-fast cascade & benchmark-based local 3B selection

    IDKHowToCodeFr
    e67482e

  2. new files

    IDKHowToCodeFr
    6f519fd

  3. final commit

    Rachit-Mangawa
    6d6ea97

  1. final commit

    Rachit-Mangawa
    19836c6

  1. feat: implement high-intelligence model rotation pool (v8.0) and align infrastructure

    Rachit-Mangawa
    9e6280a

  1. fix(infra): align Docker port with README and app.py (8080)

    Rachit-Mangawa
    d892581

  2. feat: Scalable Multi-Agent Orchestrator (v7.0) with Multi-Key Rotation and FAST_TEST mode

    Rachit-Mangawa
    08b98ed

  3. feat(infra): implement 5-tier hierarchical inference engine with key rotation

    Rachit-Mangawa
    42c83f7

  4. docs: generate high-fidelity Platinum v4.1 technical documentation

    Rachit-Mangawa
    fd5b9aa

  5. fix: apply critical tick timeout fix and schema elasticity for perfect 50/50 score

    Rachit-Mangawa
    3858fba

  6. fix(infra): upgrade OpenRouter hierarchy and sanitize health check schema

    Rachit-Mangawa
    2ce8902

  7. fix(api): refactor OpenRouter call with model hierarchy and mandatory headers

    Rachit-Mangawa
    83674d5

  8. perf: reduce num_predict to 80 for sub-20s inference on CPU

    Rachit-Mangawa
    be5289d

  9. perf: optimize local inference speed and increase internal timeout to 28s

    Rachit-Mangawa
    f673c95

  10. fix: sanitize health check schema and relocate model status to metadata

    Rachit-Mangawa
    a219be1

  11. feat: Upgrade to Llama 3.2 (3B) for superior autonomous reasoning

    Rachit-Mangawa
    7580459

  12. feat: evidence-based grounding anchors with generalized system prompt

    Rachit-Mangawa
    801d089

  13. fix: resolve message field mismatch, add hostility detection, and refine intent transition

    Rachit-Mangawa
    7e9d7e2

  14. feat: prioritize seasonal beats and trend signals for knowledge-driven engagement

    Rachit-Mangawa
    b583ed9

  15. feat: Autonomous Local-First Engine (SmollM2-1.7B) with API fallback

    Rachit-Mangawa
    c508545

  16. perf: Optimize for 30s timeout w/ SmollM2-1.7B and parallel execution

    Rachit-Mangawa
    4be69d9

  17. fix(deploy): add zstd dependency for ollama extraction

    Rachit-Mangawa
    c21f62a

  18. fix(deploy): use official ollama install script to fix 404 binary error

    Rachit-Mangawa
    d3dc97d

  19. feat: Integrate local Phi-3.5 fallback for API resilience

    Rachit-Mangawa
    7f971bd

  1. docs: update README.md with caveman style and HF metadata

    Rachit-Mangawa
    323c8ef

  2. chore(deploy): add README.md with Hugging Face Space configuration

    Rachit-Mangawa
    9d5af77

  3. refactor(deploy): use direct git push to bypass sync action API bug

    Rachit-Mangawa
    45ac092

  4. fix(deploy): explicitly set private boolean to fix HF 400 error

    Rachit-Mangawa
    b6cb752

  5. fix: switch to stable community sync action

    Rachit-Mangawa
    952b95e

  6. fix: switch to official huggingface sync action

    Rachit-Mangawa
    c0d22dd

  7. feat: platinum deployment suite v1.0

    Rachit-Mangawa
    fdeeb34