Update model card with v10 eval results (92% task, 99% format)

fix: add Qwen 3.5 chat template with tool_call format (was null)

Training in progress, step 80

Training in progress, step 70

Training in progress, step 60

Training in progress, step 50

Training in progress, step 40

Training in progress, step 30

Training in progress, step 20

Training in progress, step 10

Training in progress, step 70

Training in progress, step 60

Training in progress, step 50

Training in progress, step 40

Training in progress, step 30

Training in progress, step 20

Training in progress, step 10

End of training

Training in progress, step 80

Training in progress, step 70

Training in progress, step 60

Training in progress, step 50

Training in progress, step 40

Training in progress, step 30

Training in progress, step 20

Model card: CARL env GRPO with citations, Zenodo DOIs, and usage

Training in progress, step 10

Training in progress, step 60

Training in progress, step 50

Training in progress, step 40

Training in progress, step 30

Training in progress, step 20

Training in progress, step 10

Training in progress, step 60

Training in progress, step 50

Training in progress, step 40

Training in progress, step 30

Training in progress, step 20

Training in progress, step 10

Training in progress, step 20

Training in progress, step 10

End of training

Training in progress, step 100

Training in progress, step 90

Training in progress, step 80

Training in progress, step 70

Training in progress, step 60

Training in progress, step 50

Training in progress, step 40

Training in progress, step 30