Add README with inference examples for dudez

774cc1c verified 7 months ago

1.4 kB

library_name: transformers
tags:
  - llm4mat
  - sft
  - moleculenet
base_model: LLM-Research/Llama-3.2-1B-Instruct

DUDEZ SFT Artifacts

This repository contains supervised fine-tuning artifacts generated from the llm4mat benchmark workflow.

Included Artifacts

merged model: merged

Prompt Template

Template used to build QA prompts for this dataset:

Instructions:

Predict whether the molecule with SMILES {smiles} can bind to the target protein '{target}' (1 = active, 0 = inactive).

Prediction (0/1):

Inference (Transformers)

Load merged model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "mryufei/llm4mat-sft-dudez"
subfolder = "merged"

tokenizer = AutoTokenizer.from_pretrained(repo_id, subfolder=subfolder)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    subfolder=subfolder,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

prompt = "Question: Is this molecule active?\nAnswer:"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
with torch.no_grad():
    output = model.generate(**inputs, max_new_tokens=128, temperature=0.1)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Notes

Training/evaluation scripts are from this project workflow.
Recommended prompt format: follow the benchmark prompt template used for this dataset.