Llama-2-7b-chat-smile-finetune

Model Card

Model Description

This is a fine-tuned version of Llama-2-7b-chat, adapted for predicting drug names based on chemical properties. Given parameters like InChI, SMILES, HBD, and logP, this model generates probable drug names.

Model Details

• Developed by: Stanley Tulani Ndlovu
• Model type: Text Generation
• Language(s): English
• License: [Specify License Here]
• Finetuned from model: Llama-2-7b-chat

Uses

Direct Use

• Predicting drug names: Given a set of chemical parameters, the model predicts the name of a drug.

Out-of-Scope Use

• The model should not be used for predicting drug effectiveness or other medical diagnoses.

Bias, Risks, and Limitations

• Bias: The model might have inherent biases based on the data it was trained on.
• Limitations: The model's predictions are based on learned patterns and may not always be accurate or reliable.

Recommendations

Users should verify predictions with domain experts and use this model as a supplementary tool rather than a definitive source.

How to Get Started with the Model

from transformers import LlamaTokenizer, LlamaForCausalLM

# Load model and tokenizer
model_name = "webs911/Llama-2-7b-chat-smile-finetune"
tokenizer = LlamaTokenizer.from_pretrained(model_name)
model = LlamaForCausalLM.from_pretrained(model_name)

def predict_drug_name(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(**inputs, max_new_tokens=200)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Example usage
prompt = "Predict the drug name given the following parameters:\nInChI: ...\nSMILES: ...\nHBD: ...\nlogP: ..."
print(predict_drug_name(prompt))