Training in progress, step 1

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

@@ -28,10 +28,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
     "k_proj",
-    "q_proj"
+    "q_proj",
+    "v_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 sha256:0fd4263433bb05dd4a2e0b31ceb3c1853af3c206a099373204c8b1eaf2de4404
+oid sha256:a3009207c44ba0dbdfe900c5bd2b519dc156800e8a45b549e1dd239624ba679f
 size 60189176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a543ee8344bb51ed42a43049b6786df74542d52ce86c8ae8ad67f92fff3d476a
+oid sha256:7679b6919b9397d5832c7324de2c0adee1642957d457c5a53d289be74ebaa7ea
 size 6161