changed chat dataset.

2026-01-09 17:30:34 -05:00
parent c78a31362a
commit 0537a5df64
2 changed files with 7 additions and 6 deletions
--- a/train.py
+++ b/train.py
@@ -23,8 +23,8 @@ hypr = {
    "encoding":    "gpt2",
    "dataset":     "HuggingFaceTB/smollm-corpus",
    "subset":      "cosmopedia-v2",
-    "chat_dataset": "yahma/alpaca-cleaned",
-    "chat_subset":  None,
+    "chat_dataset": "HuggingFaceTB/smoltalk",
+    "chat_subset":  "all",
    "half":         False,
 }