fix: correct base_model to Qwen3-4B-Instruct-2507

README.md

@@ -10,7 +10,7 @@ tags:
 - information-retrieval
 library_name: transformers
 pipeline_tag: feature-extraction
-base_model: Qwen/Qwen3-4B
+base_model: Qwen/Qwen3-4B-Instruct-2507
 datasets:
 - xlangai/BRIGHT
 model-index:
@@ -175,7 +175,7 @@ print(f"Embedding shape: {embedding.shape}")
 
 ## Training
 
-MRE-T1 is trained using a two-stage approach on the Qwen3-4B base model:
+MRE-T1 is trained using a two-stage approach on the Qwen3-4B-Instruct-2507 base model:
 1. **Stage 1**: Supervised fine-tuning with task-specific reasoning prompts
 2. **Stage 2**: Reinforcement learning to optimize retrieval quality