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

README.md

@@ -27,17 +27,17 @@ 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/efvevbg6) 
+ 
 
 
 This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.24.0
+- TRL: 0.25.1
 - Transformers: 4.57.1
 - Pytorch: 2.7.0+cu128
-- Datasets: 4.2.0
+- Datasets: 4.4.1
 - Tokenizers: 0.22.1
 
 ## Citations

adapter_config.json

@@ -28,10 +28,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
+    "v_proj",
     "q_proj",
-    "v_proj"
+    "k_proj",
+    "o_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 sha256:5892c75dc318cd561e3b1ec3e32143ea1e9c8bbd4b9511b7290eb95ed288cfb4
+oid sha256:e4405c22b2a4d5be1a0c10689e9f10fd3e64cfaaad3a5c05475bcea6bbf74a71
 size 60189176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a66f5e82167bb27f1d9d62120451b1e7349b7951e1700cec16a4153edfee63
+oid sha256:26c55c21afeeed9d41d2d5843a7e3232bd43415ac8ab47ed3851fc1b68f3ba3d
 size 6289