HauserGroup/ApeTokenizer-SMILES
https://huggingface.co/HauserGroup/ApeTokenizer-SMILESApeTokenizer-SMILES is an Atom Pair Encoding (APE) tokenizer for SMILES strings, trained on ~2M unique canonical SMILES from ChEMBL 36. It is the SMILES counterpart to ApeTokenizer-SELFIES, released alongside ModernMolBERT.
Sourced from
- HuggingFace — HauserGroup/ApeTokenizer-SMILES
Related resources
Aurigene-AI/ChemFM-1B
by Aurigene-AISee the upstream model card for full details, training data and citation.
Aquiles-ai/Chargaff-Tokenizer
by Aquiles-aiByte-level BPE tokenizer for Chargaff, our DNA prediction model. No training, no merges: 1 token per UTF-8 byte.
mradermacher/SEMIKONG-70B-v2-GGUF
by mradermacherIf you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
mradermacher/ChemDFM-v1.5-8B-GGUF
by mradermacherIf you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Using llama.cpp release b2440 for quantization.
# ChemGPT 4.7M ChemGPT is based on the GPT-Neo model and was introduced in the paper Neural Scaling of Deep Chemical Models.