End of training

README.md

@@ -1,9 +1,13 @@
 ---
 base_model: Qwen/Qwen2.5-VL-3B-Instruct
+datasets: smolagents/aguvis-stage-2
 library_name: transformers
 model_name: Qwen2.5-VL-3B-Instruct-Agentic
 tags:
 - generated_from_trainer
+- open-r1
+- vision-language
+- vlm
 - trl
 - sft
 licence: license
@@ -11,7 +15,7 @@ licence: license
 
 # Model Card for Qwen2.5-VL-3B-Instruct-Agentic
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct).
+This model is a fine-tuned version of [Qwen/Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) on the [smolagents/aguvis-stage-2](https://huggingface.co/datasets/smolagents/aguvis-stage-2) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -70,7 +70,7 @@
   },
   "torch_dtype": "bfloat16",
   "transformers_version": "4.52.3",
-  "use_cache": false,
+  "use_cache": true,
   "use_sliding_window": false,
   "video_token_id": 151656,
   "vision_config": {