Qwen2.5-14B-Instruct_16

README.md

@@ -28,7 +28,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/radchenko-pn-ukrainian-catholic-university/NER_SFT/runs/1p8x2zjk) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/radchenko-pn-ukrainian-catholic-university/NER_SFT/runs/kkeqz91i) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "k_proj",
     "o_proj",
+    "down_proj",
     "up_proj",
-    "gate_proj",
-    "k_proj",
     "q_proj",
-    "down_proj"
+    "v_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87700e61239d8f27dbd786c90ca3ceae78e03f85bce9d744920b509d43278994
+oid sha256:c9ba8ee7db7d64cb147b96100c715853a311d619203c89e0e25bdae9b667a103
 size 275341720

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:142b23fa8338d41ca7f53ea7c6675c7199d453ce9834d42a8ef1c259401561d1
+oid sha256:d6b433b835f9536a7c213aeab706e4d4119e9b7fefbe2b38a4a09dab94861835
 size 5624