End of training

README.md

@@ -1,9 +1,11 @@
 ---
 base_model: Qwen/Qwen2-VL-2B-Instruct
+datasets: MMInstruction/Clevr_CoGenT_TrainA_R1
 library_name: transformers
 model_name: Qwen2-VL-2B-Instruct-SFT-Clevr_CoGenT_TrainA_R1
 tags:
 - generated_from_trainer
+- R1-V
 - trl
 - sft
 licence: license
@@ -11,7 +13,7 @@ licence: license
 
 # Model Card for Qwen2-VL-2B-Instruct-SFT-Clevr_CoGenT_TrainA_R1
 
-This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct).
+This model is a fine-tuned version of [Qwen/Qwen2-VL-2B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) on the [MMInstruction/Clevr_CoGenT_TrainA_R1](https://huggingface.co/datasets/MMInstruction/Clevr_CoGenT_TrainA_R1) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

config.json

@@ -32,7 +32,7 @@
   "tie_word_embeddings": true,
   "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": {

tokenizer_config.json

@@ -138,6 +138,7 @@
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",
   "padding_side": "left",
+  "processor_class": "Qwen2VLProcessor",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",
   "unk_token": null