End of training

README.md

@@ -1,17 +1,19 @@
 ---
 base_model: Qwen/Qwen2.5-VL-7B-Instruct
+datasets: ccvl/OpenImages_3DSR_mar16_filtered1200_nothinking
 library_name: transformers
-model_name: Qwen2.5-VL-7B-Instruct-SFT-OpenImages_3DSR_mar16_filtered1200_nothinking-2025-03-27-03-50-11
+model_name: Qwen/Qwen2.5-VL-7B-Instruct
 tags:
 - generated_from_trainer
+- open-r1
 - trl
 - sft
 licence: license
 ---
 
-# Model Card for Qwen2.5-VL-7B-Instruct-SFT-OpenImages_3DSR_mar16_filtered1200_nothinking-2025-03-27-03-50-11
+# Model Card for Qwen/Qwen2.5-VL-7B-Instruct
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct).
+This model is a fine-tuned version of [Qwen/Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) on the [ccvl/OpenImages_3DSR_mar16_filtered1200_nothinking](https://huggingface.co/datasets/ccvl/OpenImages_3DSR_mar16_filtered1200_nothinking) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -32,7 +32,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.49.0.dev0",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,
   "vision_config": {