[P0] Threshold + Params for big model #321

Closed @tcharchian opened 2025-09-03 22:57 UTC 0 comments Updated 2025-09-16 22:30 UTC
  1. Threshold + Params for big model;
  2. Scripts to compute, re-check for existing;

  3. New Models

  4. Qwen3-235B-A22B-Instruct-2507

  5. gpt-oss-120b
  6. DeepSeek-R1-0528
  7. gemma-3-27b-it
  8. Qwen3-30B-A3B-Instruct-2507

  9. gpt-oss-20b

  10. Instruction to do it

  11. Inference Validation finetuning;

🔄 Auto-synced from Issue #321 every hour.