Instructions to use language-plus-molecules/mCLM_1k-3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use language-plus-molecules/mCLM_1k-3b with Transformers:

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

pipe = pipeline("text-generation", model="language-plus-molecules/mCLM_1k-3b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("language-plus-molecules/mCLM_1k-3b")
model = AutoModelForCausalLM.from_pretrained("language-plus-molecules/mCLM_1k-3b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use language-plus-molecules/mCLM_1k-3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "language-plus-molecules/mCLM_1k-3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "language-plus-molecules/mCLM_1k-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/language-plus-molecules/mCLM_1k-3b

SGLang

How to use language-plus-molecules/mCLM_1k-3b 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 "language-plus-molecules/mCLM_1k-3b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "language-plus-molecules/mCLM_1k-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "language-plus-molecules/mCLM_1k-3b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "language-plus-molecules/mCLM_1k-3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use language-plus-molecules/mCLM_1k-3b with Docker Model Runner:
```
docker model run hf.co/language-plus-molecules/mCLM_1k-3b
```

mCLM_1k-3b

File size: 976 Bytes

10a47d3

# mCLM Usage Example

import torch
from transformers import AutoTokenizer
from mCLM.model.qwen_based.model import Qwen2ForCausalLM
from mCLM.tokenizer.molecule_tokenizer import MoleculeTokenizer

# Load model and tokenizers
model = Qwen2ForCausalLM.from_pretrained(
    "YOUR_REPO_ID",
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained("YOUR_REPO_ID")
tokenizer.pad_token = tokenizer.eos_token

# Load molecule tokenizer
torch.serialization.add_safe_globals([MoleculeTokenizer])
molecule_tokenizer = torch.load("molecule_tokenizer.pth", weights_only=False)

# Run inference
user_input = "What is aspirin used for?"
messages = [{"role": "user", "content": user_input}]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")

outputs = model.generate(input_ids=inputs, max_new_tokens=256)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)