Oct 27 15 days ago

1. 05:58

   Restore model card metadata

   jsemrau
   Verified signature

   447ebdf
2. 04:18

   Update README.md

   jsemrau
   Verified signature

   77c3745
3. 04:17

   Update README.md

   jsemrau
   Verified signature

   4fb0d2c
4. 04:12

   Rename to Arbiter-8B; state the Qwen3-8B base clearly

   jsemrau
   Verified signature

   cb5578c
5. 03:19

   Model card: requirements instead of test-machine details

   jsemrau
   Verified signature

   a6f9510
6. 03:18

   Model card: standard model details, how it works, versions

   jsemrau
   Verified signature

   22b8aa7
7. 03:16

   Update README.md

   jsemrau
   Verified signature

   bd24611
8. 03:10

   Arbiter v0.4 full model: LoRA merged into the dequantized 4-bit base (fp16), tokenizer, decision head, calibration; adapter kept in adapter/

   jsemrau
   Verified signature

   aa20e73
9. 02:34

   Arbiter v0.4: LoRA adapter, decision head, calibration, inference code and model card

   jsemrau
   Verified signature

   53ab3d4
10. 02:26

    initial commit

    jsemrau
    Verified signature

    e7590c6