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/ax4zjmnd) 
+[<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/xd6oo3po) 
 
 
 This model was trained with SFT.
@@ -37,8 +37,8 @@ This model was trained with SFT.
 
 - TRL: 0.14.0
 - Transformers: 4.47.1
-- Pytorch: 2.5.1+cu124
-- Datasets: 3.2.0
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.3.2
 - Tokenizers: 0.21.0
 
 ## Citations

adapter_config.json

@@ -26,10 +26,10 @@
     "gate_proj",
     "q_proj",
     "k_proj",
-    "v_proj",
     "up_proj",
+    "down_proj",
     "o_proj",
-    "down_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:422af23f4ae5b3b82d760f3506a9238e6846e74ca787b33b93de4e57a389c9f3
+oid sha256:6106c60e26acaf9387ee0c7d14d1ff2867a9d6b0c0bec4ca6565dcdeec6f1b48
 size 275341720

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9045f2a71bf96bc6d055f6e755138fc6861427ada644b759baf0b7465a54575
+oid sha256:1bd556daaf4a04a9c7527b93d0f1862f723f686bdee0b8d847b740833eb44498
 size 5624