<<Eric-Tsai>>/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/yichuntsai/huggingface/runs/lp4p4k2u)
+[<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/yichuntsai/huggingface/runs/3ru4d4l6)
 
 This model was trained with SFT.
 

adapter_config.json

@@ -22,10 +22,10 @@
   "target_modules": [
     "gate_proj",
     "down_proj",
-    "up_proj",
+    "q_proj",
     "k_proj",
     "o_proj",
-    "q_proj",
+    "up_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:033bf505aa390e1a238a902ee9b204e6445bef8e7612f89fccd3c4bb5edd9982
+oid sha256:ca4418aa81612afc3a300b43dd952dd5a0ed393a3638f888aa996aeef7d68ce9
 size 167832240

runs/Nov12_16-31-56_c211e9ae9307/events.out.tfevents.1731431041.c211e9ae9307.5688.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14b11cae0b6a09afe46ec11b888fedf39ea80b0d173d523eb63c3aa347f29cad
+size 22503

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db4af4db58d271aecabe25fc8cb0d5d7e645aca1176fe7b814a09b08189e5086
+oid sha256:4576e1311687abd459e8290fb3878ae9cbd334d240e0b50559e3de750385ce59
 size 5624