Add training workflow, datasets, and runbook

2025-12-23 21:17:22 -08:00
commit 619e87aacc
2140 changed files with 2513895 additions and 0 deletions
--- a/training_data/lora_adapter/special_tokens_map.json
+++ b/training_data/lora_adapter/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|return|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}