Instructions to use language-plus-molecules/Meditron7b-caption2smiles-LPM24 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use language-plus-molecules/Meditron7b-caption2smiles-LPM24 with Transformers:

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

pipe = pipeline("text-generation", model="language-plus-molecules/Meditron7b-caption2smiles-LPM24")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("language-plus-molecules/Meditron7b-caption2smiles-LPM24")
model = AutoModelForCausalLM.from_pretrained("language-plus-molecules/Meditron7b-caption2smiles-LPM24")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use language-plus-molecules/Meditron7b-caption2smiles-LPM24 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "language-plus-molecules/Meditron7b-caption2smiles-LPM24"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "language-plus-molecules/Meditron7b-caption2smiles-LPM24",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/language-plus-molecules/Meditron7b-caption2smiles-LPM24

SGLang

How to use language-plus-molecules/Meditron7b-caption2smiles-LPM24 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/Meditron7b-caption2smiles-LPM24" \
    --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": "language-plus-molecules/Meditron7b-caption2smiles-LPM24",
		"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 "language-plus-molecules/Meditron7b-caption2smiles-LPM24" \
        --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": "language-plus-molecules/Meditron7b-caption2smiles-LPM24",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use language-plus-molecules/Meditron7b-caption2smiles-LPM24 with Docker Model Runner:
```
docker model run hf.co/language-plus-molecules/Meditron7b-caption2smiles-LPM24
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

Model Details

Below is the prompt used for the model:

prompt_template =     ("Below is an instruction that describes a task, paired with an input that provides further context. "
        "Write a response that appropriately completes the request.\n\n"
        "### Instruction:\n"
        "You are a researcher. You can come up molecule smile strings based on your existing knowledge. "
        "Molecule smile strings are given against the following input. You should be as detailed as possible.\n\n"
        "### Input:\nCaption: %s \nIn that caption, could you generate a molecule smile string?\n\n\n### Response:")

Downloads last month: 9

Safetensors

Model size

7B params

Tensor type

F32

Model tree for language-plus-molecules/Meditron7b-caption2smiles-LPM24

Quantizations

1 model

Collection including language-plus-molecules/Meditron7b-caption2smiles-LPM24

LPM-24

Collection