Instructions to use ddidacus/RS-mol-llama-1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ddidacus/RS-mol-llama-1b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ddidacus/RS-mol-llama-1b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ddidacus/RS-mol-llama-1b")
model = AutoModelForCausalLM.from_pretrained("ddidacus/RS-mol-llama-1b")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ddidacus/RS-mol-llama-1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ddidacus/RS-mol-llama-1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ddidacus/RS-mol-llama-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ddidacus/RS-mol-llama-1b

SGLang

How to use ddidacus/RS-mol-llama-1b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ddidacus/RS-mol-llama-1b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ddidacus/RS-mol-llama-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ddidacus/RS-mol-llama-1b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ddidacus/RS-mol-llama-1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ddidacus/RS-mol-llama-1b with Docker Model Runner:
```
docker model run hf.co/ddidacus/RS-mol-llama-1b
```

Mol-MoE: Training Preference-Guided Routers for Molecule Generation

Diego Calanzone (1, 2), Pierluca D'Oro (2), Pierre-Luc Bacon (1, 2)
(1) Universite de Montreal, (2) Mila Quebec AI Institute
arXiv: https://arxiv.org/abs/2502.05633

Abstract: Recent advances in language models have enabled framing molecule generation as sequence modeling. However, existing approaches often rely on single-objective reinforcement learning, limiting their applicability to real-world drug design, where multiple competing properties must be optimized. Traditional multi-objective reinforcement learning (MORL) methods require costly retraining for each new objective combination, making rapid exploration of trade-offs impractical. To overcome these limitations, we introduce Mol-MoE, a mixture-of-experts (MoE) architecture that enables efficient test-time steering of molecule generation without retraining. Central to our approach is a preference-based router training objective that incentivizes the router to combine experts in a way that aligns with user-specified trade-offs. This provides improved flexibility in exploring the chemical property space at test time, facilitating rapid trade-off exploration. Benchmarking against state-of-the-art methods, we show that Mol-MoE achieves superior sample quality and steerability.

How to use this model

This LM is fine-tuned to generate molecules in the SMILES format wrt. desired properties. For unconditioned SMILES generation, use the BOS token <s>.
For conditioned generation, please refer to the paper and the official codebase to derive different conditioned models.
This model is the merging result of 5 fine-tuned versions (JNK3, DRD2, GSK3B, CYP2D6, CYP2D19) with equal interpolation weight: w_i = 0.2.

An example of the generation pipeline:

from transformers import AutoTokenizer, AutoModelForCausalLM
import re

# Setup
device = "cuda"
tokenizer = AutoTokenizer.from_pretrained("ddidacus/RS-mol-llama-1b")
model = AutoModelForCausalLM.from_pretrained("ddidacus/RS-mol-llama-1b")
generation_kwargs = {
    "max_new_tokens": 128,
    "min_length": -1,
    "top_k": 0.0,
    "top_p": 0.9,
    "do_sample": True,
    "pad_token_id": tokenizer.eos_token_id,
    "temperature": 1.0
}

# Inference
query = "<s>"
toks = tokenizer([query], return_tensors="pt")["input_ids"].to(device)
output = model.generate(toks, **generation_kwargs)
output = tokenizer.batch_decode(output)

# Parsing
filter = r'<s>(.*?)</s>'
molecule = re.findall(filter, output[0], re.DOTALL)