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

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/dz42vc1n) 
+ 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -28,10 +28,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "v_proj",
     "k_proj",
-    "q_proj"
+    "o_proj",
+    "q_proj",
+    "v_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:d7cacfe5947cbee40d393abe72bef9d24fd185cead4c02179818f8b59ff1c646
+oid sha256:d6f5538f07032567e3bce56880036f97e7b64b064fa6329689d5d542a57721bc
 size 60189176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5576a54c04dd946e82a36b657527fcd86acf1de38b4b2630c533a75b4b90180d
+oid sha256:79b401cd1b9a09aa2b3f0742d7927004fdae784f8288e61331735838d238d9a8
 size 6225