baseten-admin/gpt-oss-20b-multilingual-reasoner-e2e

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/philipkiely-baseten/huggingface/runs/lim8bpfb) 
+[<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/philipkiely-baseten/huggingface/runs/e8pxodtr) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -30,8 +30,8 @@
   "target_modules": [
     "o_proj",
     "v_proj",
-    "k_proj",
-    "q_proj"
+    "q_proj",
+    "k_proj"
   ],
   "target_parameters": [
     "7.mlp.experts.gate_up_proj",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c1a715bbfc0b237e3d200a5fe17f5a634a8a6dc56ec07f8e262cc42909aa68
+oid sha256:9f2c1e3fa5f0e0dbe4f78a19da609af70d38b94b2369e7f9dd754c88ff5db385
 size 60189176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a51021a14fa32c91aae3f812267611990bb923af9d13c42b22fb58565cb4520
+oid sha256:14813bf1c4edc67c28a5b6fadd5f3526958f05e9f222870e2f6262b54a4b211d
 size 6289