mbudisic/llama381binstruct_summarize_short

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/mbudisic-framatome-inc-/huggingface/runs/gdqlm90s) 
+[<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/mbudisic-framatome-inc-/huggingface/runs/jimgu88v) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -24,13 +24,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
     "k_proj",
+    "o_proj",
     "gate_proj",
+    "q_proj",
+    "down_proj",
     "up_proj",
-    "v_proj",
-    "down_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c1d9c85cb4455970ca81a04f85bbdf17966818a9fb052577949c3dd28742d9
+oid sha256:4840ef96d71285d25ee61a67a740f3207fc66133bb2b98023498f38a0cfa42db
 size 167832240

runs/Mar21_19-18-44_26c61baf10fe/events.out.tfevents.1742584729.26c61baf10fe.1139.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a195ccf53d8622fd963c610f4012325fa5f06f8c4f27658d15cb0170731dbe
+size 26898

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21045cc755641a84969f681a463ee4615d5a4c07ae791984db64014f726fb559
+oid sha256:2c3ceedcde6bd203ee8df5950ba39db3f23fe8e2f1558d5545ccf5b6b99b5002
 size 5688