CodeDevX/MultiModel-Small-229M

MultiModel Small 229M

Small multimodal-ready transformer checkpoint trained on the project's educational text dataset.

Details

• Parameters: approximately 229M
• Text decoder: 12 layers, 768 hidden size, 12 attention heads
• Vocabulary: 50,257 BPE tokens
• Training samples: 1,000
• Checkpoint: global step 350

Files

• pytorch_model.bin: PyTorch state dictionary
• config.json: model configuration
• tokenizer.json and tokenizer_config.json: uploaded at repository root

This checkpoint uses the custom model implementation in the source project and is not directly loadable with AutoModel.