Update README.md

README.md

@@ -14,45 +14,16 @@ pipeline_tag: image-to-text
 
 This is a fine-tuned version of Qwen2.5-VL for enhanced reasoning capabilities, specifically optimized for multimodal reasoning tasks.
 
-## Model Details
-
-- **Base Model**: qwen2.5-vl
-- **Model Type**: Vision-Language Model
-- **Task**: Multimodal reasoning and visual question answering
-- **Fine-tuning**: Custom training on reasoning datasets
-
-## Model Files
-
-This repository contains only the essential files for inference:
-
-### Core Model Files
-- `config.json`: Model configuration
-- `generation_config.json`: Text generation configuration
-- `model-*.safetensors`: Model weights in SafeTensors format
-- `model.safetensors.index.json`: Model weights index
-
-### Tokenizer Files
-- `tokenizer.json`: Tokenizer configuration
-- `tokenizer_config.json`: Tokenizer settings
-- `vocab.json`: Vocabulary file
-- `merges.txt`: BPE merge rules
-- `added_tokens.json`: Additional tokens
-- `special_tokens_map.json`: Special token mappings
-
-### Vision Processing
-- `preprocessor_config.json`: Image preprocessing configuration
-- `chat_template.json`: Chat template for conversations
-
 ## Usage
 
 ```python
-from transformers import AutoModelForCausalLM, AutoProcessor
+from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
 import torch
 
 model_id = "ChaoHuangCS/DRIFT-VL-7B"
 
 # Load model and processor
-model = AutoModelForCausalLM.from_pretrained(
+model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
     model_id,
     torch_dtype=torch.float16,
     device_map="auto",
@@ -88,6 +59,7 @@ print(response)
 
 This model was fine-tuned using:
 - **Base Model**: Qwen2.5-VL
+- **Merged Model**: DeepSeek-R1
 - **Training Method**: Custom reasoning-focused fine-tuning
 - **Dataset**: Multimodal reasoning datasets
 - **Architecture**: Preserves original Qwen2.5-VL architecture
@@ -102,7 +74,7 @@ The model has been optimized for:
 
 ## Citation
 
-If you use this model, please cite the original Qwen2.5-VL paper and mention this fine-tuned version.
+If you use this model, please cite our paper.
 
 ## License