23 days ago
-
TRL: inject text/JSON tool calls + forced ls into tool loop
-
Force first tool + tool_choice required nudge
-
Fix Langfuse ckpt/heldout child trace_context
-
Smoke mode + detailed train entry
-
Add kaggle/train_grpo.py
-
Add kaggle/train_grpo.py
-
Add kaggle/train_grpo.py
-
Add kaggle/train_grpo.py
-
Add kaggle/train_grpo.py
-
Add kaggle/train_grpo.py
-
Add kaggle/train_grpo.py
-
Add kaggle/train_grpo.py
-
Add kaggle/KAGGLE_SETUP.md
-
Add kaggle/train_grpo.py
-
Add kaggle/train_grpo.py
-
Add kaggle/KAGGLE_SETUP.md
-
Add kaggle/train_grpo.py
-
Add kaggle/KAGGLE_SETUP.md
-
Add kaggle/train_grpo.py
-
Add kaggle/KAGGLE_SETUP.md
-
Add kaggle/train_grpo.py
-
Add kaggle/train_grpo.py
-
Add kaggle/KAGGLE_SETUP.md
-
Add kaggle/train_grpo.py