Model save

README.md

@@ -1,6 +1,5 @@
 ---
 base_model: openai/gpt-oss-20b
-datasets: HuggingFaceH4/Multilingual-Thinking
 library_name: transformers
 model_name: gpt-oss-20b-multilingual-reasoner
 tags:
@@ -12,7 +11,7 @@ licence: license
 
 # Model Card for gpt-oss-20b-multilingual-reasoner
 
-This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b) on the [HuggingFaceH4/Multilingual-Thinking](https://huggingface.co/datasets/HuggingFaceH4/Multilingual-Thinking) dataset.
+This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

adapter_config.json

@@ -30,8 +30,8 @@
   "target_modules": [
     "o_proj",
     "k_proj",
-    "v_proj",
-    "q_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:f2d1db61767ff6413241b79cb21a24702bb2892ec3548fcaf7d52df745cc5d44
+oid sha256:61738bcb658b1d25478670a3fd9b5b33484a706661543cf12a4a4e0f815748c5
 size 60189176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd761debcb32d7d37acd1e45cf710eb40ebee889740963171e607916a8c1ca8c
+oid sha256:ab6b151b7d14c45bff9441ac61499765012170ca092a1c19aed262de85956690
 size 6161