fix docs and comments

garyzhang99 · garyzhang99 · commit fea166672fcf · 2025-12-19T13:39:18.000+08:00
diff --git a/examples/opd_gsm8k/README.md b/examples/opd_gsm8k/README.md
@@ -22,7 +22,7 @@ Download the model checkpoint and modify your config file, then run:
 trinity run examples/opd_gsm8k/opd_gsm8k.yaml
 ```
 
-Then you are all set! It should be pretty simple😄, and the training should converge very quick(Much quicker then RL).
+Then you are all set! It should be pretty simple😄, and the training should converge very quick.
 
 
 
diff --git a/trinity/algorithm/advantage_fn/__init__.py b/trinity/algorithm/advantage_fn/__init__.py
@@ -17,7 +17,6 @@
         "asymre": "trinity.algorithm.advantage_fn.asymre_advantage.ASYMREGroupAdvantage",
         "asymre_verl": "trinity.algorithm.advantage_fn.asymre_advantage.ASYMREAdvantageFn",
         "rec": "trinity.algorithm.advantage_fn.rec_advantage.RECGroupedAdvantage",
-        # On-policy distillation
         "on_policy_distill": "trinity.algorithm.advantage_fn.on_policy_distill_advantage.OnPolicyDistillAdvantage",
     },
 )

Original file line number	Diff line number	Diff line change
`@@ -17,7 +17,6 @@`
`17`	`17`	`"asymre": "trinity.algorithm.advantage_fn.asymre_advantage.ASYMREGroupAdvantage",`
`18`	`18`	`"asymre_verl": "trinity.algorithm.advantage_fn.asymre_advantage.ASYMREAdvantageFn",`
`19`	`19`	`"rec": "trinity.algorithm.advantage_fn.rec_advantage.RECGroupedAdvantage",`
`20`		`- # On-policy distillation`
`21`	`20`	`"on_policy_distill": "trinity.algorithm.advantage_fn.on_policy_distill_advantage.OnPolicyDistillAdvantage",`
`22`	`21`	`},`
`23`	`22`	`)`