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

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: gpt-oss-20b-multilingual-reasoner
 tags:
 - generated_from_trainer
-- sft
 - trl
+- sft
 licence: license
 ---
 
@@ -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/11tap9lm) 
+[<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/rgkdmqkl) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -28,10 +28,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
     "o_proj",
-    "q_proj"
+    "q_proj",
+    "k_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 sha256:7cfdf2c24c5b951d7a361a425307e19aa178394a47d7b19986b78c8b85f24d6f
+oid sha256:9a76bc8736aaad5ce7dec89eb155ff35dac7e0700a0e9d5ac9f663b40b4e7233
 size 60189176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797f4b67ccad0feb5247bd5a007b2c3c8edb0de9415a1f699e51390656762d57
+oid sha256:641a469654a61353a7935807fbda45fb5619169b26648f988a956b184bde304f
 size 6225