Instructions to use anonymous-vicor/ViCoR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anonymous-vicor/ViCoR with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("anonymous-vicor/ViCoR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download NOTICE from anonymous-vicor/ViCoR: direct link, hf CLI and curl.
- Browser
- Download file 606 Bytes
-
https://huggingface.co/anonymous-vicor/ViCoR/resolve/main/NOTICE
- Command line
-
hf download hf://anonymous-vicor/ViCoR/NOTICE
-
curl -L -o NOTICE https://huggingface.co/anonymous-vicor/ViCoR/resolve/main/NOTICE
606 Bytes
| Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved. | |
| Built with Qwen. | |
| The ViCoR model weights are a fine-tuned and merged derivative of Qwen2.5-VL-3B-Instruct. The model parameters, generation settings, processor settings and prompts are adapted for molecular graph verification and revision. Tokenizer resources retain the upstream vocabulary. | |
| MolScribe is distributed with its Apache-2.0 license. Its inference checkpoint has been repackaged to remove optimizer, scheduler and training-step state; all encoder and decoder tensors are unchanged. | |