taronklm/Qwen2.5-0.5B-Instruct-chatbot

README.md

@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 0.0001
 - train_batch_size: 1
 - eval_batch_size: 8
 - seed: 42

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
-    "k_proj",
     "v_proj",
-    "gate_proj",
     "q_proj",
-    "down_proj"
+    "down_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj"
   ],
   "task_type": "CASUAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a675bde7dd92fbe4b85b6acde91ab31912b0803415bf5c768ba33fbf0c8e861
+oid sha256:2ea52e798fd0cefac0e55219209512632e2c2cf5b4b119151e5ad278ad8b050e
 size 8841592

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60392f1478e9b3ed1b32c89ae12e2ac0e14a4f9114ceae947f601344d2dfac3
+oid sha256:5da53ed7af62e936f5f554ea55838e05f82d9d7d5f05b9abe72d2005dfecf1ff
 size 5368