Update README.md

README.md

@@ -12,7 +12,7 @@ tags:
 This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
 
 ## Model Details
-Chem_Fuser is a prototype base model that explores the use of diffusion-inspired transformers for SMILES sequence completion. It represents an early proof-of-concept for unmasking partial chemical structures using learned context and token diffusion.
+Chemfuser is a prototype base model that explores the use of diffusion-inspired transformers for SMILES sequence completion. It represents an early proof-of-concept for unmasking partial chemical structures using learned context and token diffusion.
 
 This is the first in a planned series of models aimed at general-purpose molecular generation, inpainting, and drug design. Work is actively ongoing to expand its capabilities, integrate richer chemical priors, and train larger and more expressive versions for broader applicability across medicinal chemistry, cheminformatics, and materials science.
 
@@ -39,8 +39,8 @@ You can use this model directly via the Hugging Face `pipeline`:
 from transformers import AutoTokenizer, pipeline
 
 # Load tokenizer and pipeline
-tokenizer = AutoTokenizer.from_pretrained("kelu01/Chem_Fuser")
-pipe = pipeline("smiles-diffusion", model="kelu01/Chem_Fuser", voc=tokenizer, trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained("kelu01/Chemfuser")
+pipe = pipeline("smiles-diffusion", model="kelu01/Chemfuser", voc=tokenizer, trust_remote_code=True)
 
 # Provide a partially masked SMILES string
 masked_smiles = "CC[MASK]N[MASK]1[MASK][MASK]C[MASK][C@H][MASK][MASK][MASK][MASK][MASK][MASK])c[MASK][MASK]c[MASK]c[MASK][MASK]C([MASK][MASK]([MASK])[MASK])c[MASK]cc[MASK]c2[MASK]cc[MASK]c[MASK]2"  # Example
@@ -50,15 +50,15 @@ print(completed)
 ```
 ## Out-of-Scope Use
 
-Chem_Fuser is not intended for the following:
+Chemfuser is not intended for the following:
 - Natural language tasks such as text generation, sentiment analysis, or question answering.
 - Direct clinical decision-making or drug safety evaluation. The model is research-grade and should not be used in medical settings without further validation.
 - Arbitrary string generation — input must be a partially masked SMILES string with valid chemical syntax.
-- Structure validation or property prediction — Chem_Fuser does not verify chemical correctness or predict bioactivity; external tools (e.g., RDKit) must be used for validation.
+- Structure validation or property prediction — Chemfuser does not verify chemical correctness or predict bioactivity; external tools (e.g., RDKit) must be used for validation.
 
 ## Bias, Risks, and Limitations
 
-While Chem_Fuser is powerful for generating chemically plausible molecules, it comes with the following limitations:
+While Chemfuser is powerful for generating chemically plausible molecules, it comes with the following limitations:
 - Chemical Validity Not Guaranteed: The model can produce syntactically correct but chemically invalid molecules. Use cheminformatics tools like RDKit to filter outputs.
 - Biological Activity Unknown: The generated molecules are not guaranteed to be biologically active or safe. Experimental validation is essential.
 - Bias in Training Data: The model is trained on publicly available databases (e.g., ZINC, ChEMBL), which are biased toward drug-like, small organic molecules. It may perform poorly on polymers, organometallics, or exotic chemical spaces.
@@ -72,7 +72,7 @@ Use the code below to get started with the model.
 
 ```python
 from transformers import AutoModel
-model = AutoModel.from_pretrained("kelu01/Chem_Fuser",trust_remote_code=True)
+model = AutoModel.from_pretrained("kelu01/Chemfuser",trust_remote_code=True)
 ```
 ## Disclaimer