LlaSMol Model

from LLM4Chem.generation import LlaSMolGeneration

generator = LlaSMolGeneration(
    "osunlp/LlaSMol-Mistral-7B", 
    device="cuda"
)

query = "Describe this molecule: <SMILES> CCOC(=O)C1=CN=CN1[C@H](C)C1=CC=CC=C1 </SMILES>"
response = generator.generate(query)
# Output: "The molecule is an imidazole derivative with short-acting sedative, 
#          hypnotic, and general anesthetic properties. Etomidate appears to have 
#          gamma-aminobutyric acid (GABA) like effects..."

query = """Give me a molecule that satisfies: The molecule is a member of the class of 
tripyrroles that is a red-coloured pigment with antibiotic properties produced by Serratia 
marcescens. It has a role as an antimicrobial agent..."""

response = generator.generate(query)
# Output: "Here is a potential molecule: <SMILES> CCCCCC1=C(C)NC(/C=C2\N=C(C3=CC=CN3)C=C2OC)=C1 </SMILES>"

MODELNAME=LlaSMol-Mistral-7B
CUDA_VISIBLE_DEVICES=0,1,2,3 accelerate launch finetune.py \
  --data_path osunlp/SMolInstruct \
  --base_model mistralai/Mistral-7B-v0.1 \
  --output_dir checkpoint/$MODELNAME

from rdkit import Chem

def canonicalize_smiles(smiles: str) -> str:
    """Convert SMILES to canonical form."""
    mol = Chem.MolFromSmiles(smiles)
    if mol is None:
        return smiles
    return Chem.MolToSmiles(mol)

@tool
def answer_chemistry_query(query: str) -> str:
    """Answer a chemistry-related query using LlaSMol."""
    response = generator.generate(query)
    return response[0]["output"][0]

# ❌ Incorrect - no tags
query = "What is the SMILES for aspirin?"

# ✅ Correct - IUPAC tagged
query = "What is the SMILES for <IUPAC> aspirin </IUPAC>?"

import plan_execute_agent.llasmol_response as llasmol_response

response = generator.generate(query)
llasmol_response.model_response = response  # Store for later access
return response[0]["output"][0]

python generate_on_dataset.py \
  --model_name osunlp/LlaSMol-Mistral-7B \
  --output_dir eval/LlaSMol-Mistral-7B/output

python extract_prediction.py \
  --output_dir eval/LlaSMol-Mistral-7B/output \
  --prediction_dir eval/LlaSMol-Mistral-7B/prediction

python compute_metrics.py \
  --prediction_dir eval/LlaSMol-Mistral-7B/prediction