sahanes/llama3181binstruct_translate_v1

README.md

@@ -27,7 +27,7 @@ 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/aidevelopemaker/huggingface/runs/ygnrohe9)
+[<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/aidevelopemaker/huggingface/runs/mre9ed8g)
 
 This model was trained with SFT.
 

adapter_config.json

@@ -24,12 +24,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "up_proj",
     "down_proj",
-    "q_proj",
-    "v_proj",
     "k_proj",
-    "gate_proj"
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6730c254a89af4cc3f01e111b22133c03fb2e9dd739b6da57a3e5297b70fb722
+oid sha256:9f1a5fa446544818f4dfe39775095dc8f987b092c2277ec34ef00b9f1325a620
 size 167832240

runs/Dec12_21-55-22_21367a8361d4/events.out.tfevents.1734040527.21367a8361d4.3033.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebfd7c54079c91af2ddad7b4c7f0d35ef186fed5365f8d4d8c09522214431ad5
+size 9727

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08589542368e4e05807a18f3e3dba8e5ac0fe5025a9638b45e642f32d94b1020
+oid sha256:46e4710fc468341b746e18d6ae2412054c2a5733f57a344eadc2be531d832858
 size 5624