Model save

README.md

@@ -27,17 +27,17 @@ 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/realdragonma-pelliculum/huggingface/runs/gucz3wwp) 
+[<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/realdragonma-pelliculum/huggingface/runs/wcdoae50) 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.14.0
-- Transformers: 4.48.3
+- TRL: 0.15.0
+- Transformers: 4.49.0
 - Pytorch: 2.6.0+cu124
-- Datasets: 3.2.0
+- Datasets: 3.3.1
 - Tokenizers: 0.21.0
 
 ## Citations

final_checkpoint/adapter_config.json

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "q_proj",
     "o_proj",
-    "v_proj",
-    "k_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

final_checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c0d86cfce92d8c1604bab7d4c9cc8c90cf852c6a21ec3bf0e5b294ed2ff9a2
+oid sha256:bf7f8b223f35118ded6f308ce0488d12a93f556f0cc1e31b007ce46ae8940916
 size 29523136

final_checkpoint/tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 1024,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

final_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:468d6144abe817c443d42dc9f38248e1b7dacc79a09c721a19ae706c7c779e73
-size 5688
+oid sha256:19ffad974e6c86ba8d10a67fd65eeaea81497bd8351104df21e2567e618973a0
+size 5624