hanyinwang
/

layer-project-diagnostic-mistral

Reinforcement Learning

Inference Endpoints

Model card Files Files and versions Community

hanyinwang commited on May 3

Commit

324c990

•

1 Parent(s): 84db619

Update config.json

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -29,12 +29,12 @@
   "ppo_epochs": 4,
   "project_kwargs": {},
   "push_to_hub_if_best_kwargs": {
-    "repo_id": "hanyinwang/layer-project-rlhf-mistral"
   },
   "query_dataset": "imdb",
   "ratio_threshold": 10.0,
   "remove_unused_columns": true,
-  "reward_model": "sentiment-analysis:lvwerra/distilbert-imdb",
   "score_clip": null,
   "seed": 0,
   "steps": 20000,

   "ppo_epochs": 4,
   "project_kwargs": {},
   "push_to_hub_if_best_kwargs": {
+    "repo_id": "hanyinwang/layer-project-diagnostic-mistral"
   },
   "query_dataset": "imdb",
   "ratio_threshold": 10.0,
   "remove_unused_columns": true,
+  "reward_model": "hanyinwang/layer-project-reward-model",
   "score_clip": null,
   "seed": 0,
   "steps": 20000,