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/0skuk31e) 
+[<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/1xo5mm9d) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -24,11 +24,11 @@
   "revision": null,
   "target_modules": [
     "down_proj",
-    "q_proj",
-    "v_proj",
-    "k_proj",
     "up_proj",
     "o_proj",
+    "v_proj",
+    "k_proj",
+    "q_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cab9aa858d59c87cd50b9d6bc7d7b4ca95b0f9d73c617e2b25362d659914de7
+oid sha256:e0524076938001e1628ed03e280f1aef6552526a2986cc7381395abfe8ba9b7a
 size 275341720

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2264ec16cbacc7ff9318c9e740a6b8df0b1942e593cc078324134715ef383b2f
+oid sha256:24320f7bb495e85254adc179c83462403f39d543291929fb56b9c4eaa9956d2a
 size 5624