gemma-2-27b-it_32

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/n3aba9m8) 
+[<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/kzk26equ) 
 
 
 This model was trained with SFT.
@@ -38,7 +38,7 @@ This model was trained with SFT.
 - TRL: 0.14.0
 - Transformers: 4.47.1
 - Pytorch: 2.5.1+cu121
-- Datasets: 3.2.0
+- Datasets: 3.3.2
 - Tokenizers: 0.21.0
 
 ## Citations

adapter_config.json

@@ -23,12 +23,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "v_proj",
     "up_proj",
+    "down_proj",
     "o_proj",
-    "v_proj",
     "gate_proj",
-    "down_proj",
+    "q_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e85456e1c6a8ab949ebee99eee64c5555aa08c05f4aca20d4e4fdd11a63b5819
+oid sha256:c675c118009525d7780271ace09d322f3668cf00a37d140a66630a06a302e044
 size 913527872

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9724ba3c058f6b54126c16bd1dccfda49227905a9a8bfae8bcc0b69bcf62827f
+oid sha256:5320d45e85fe27a78b108b88d693380082b3cc83bb5abe8d9b80205c06ed7bbc
 size 5624