Generative Chemistry & Synthesis Planning
Collection
De novo molecule generation, forward reaction prediction, retrosynthesis and molecule captioning. • 5 items • Updated
How to use Aurigene-AI/ChemFM-1B with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Aurigene-AI/ChemFM-1B") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("Aurigene-AI/ChemFM-1B")
model = AutoModelForCausalLM.from_pretrained("Aurigene-AI/ChemFM-1B", device_map="auto")How to use Aurigene-AI/ChemFM-1B with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aurigene-AI/ChemFM-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Aurigene-AI/ChemFM-1B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Aurigene-AI/ChemFM-1B
How to use Aurigene-AI/ChemFM-1B with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Aurigene-AI/ChemFM-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": "Aurigene-AI/ChemFM-1B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "Aurigene-AI/ChemFM-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": "Aurigene-AI/ChemFM-1B",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Aurigene-AI/ChemFM-1B with Docker Model Runner:
docker model run hf.co/Aurigene-AI/ChemFM-1B
Mirrored by Aurigene AI
Discovery stage: Hit generation / Lead optimization
A 1B-parameter chemistry foundation model trained on UniChem. Fine-tune it for molecule generation, property prediction or reaction tasks.
Upstream:
ChemFM/ChemFM-1B- all credit to the original authors; the model card and licence below are theirs.Explore the rest of the catalogue: Molecule Explorer - Protein Target Explorer - Drug Discovery Model Hub
See the upstream model card for full details, training data and citation.