Instructions to use MS-ML/SpecTUS_pretrained_only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MS-ML/SpecTUS_pretrained_only with Transformers:

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

pipe = pipeline("text-generation", model="MS-ML/SpecTUS_pretrained_only")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("MS-ML/SpecTUS_pretrained_only")
model = AutoModelForSeq2SeqLM.from_pretrained("MS-ML/SpecTUS_pretrained_only")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MS-ML/SpecTUS_pretrained_only with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MS-ML/SpecTUS_pretrained_only

SGLang

How to use MS-ML/SpecTUS_pretrained_only 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 "MS-ML/SpecTUS_pretrained_only" \
    --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": "MS-ML/SpecTUS_pretrained_only",
		"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 "MS-ML/SpecTUS_pretrained_only" \
        --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": "MS-ML/SpecTUS_pretrained_only",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MS-ML/SpecTUS_pretrained_only with Docker Model Runner:
```
docker model run hf.co/MS-ML/SpecTUS_pretrained_only
```

hajekad commited on Dec 2, 2024

Commit

7d1b679

verified ·

1 Parent(s): b333ffd

Update README.md

Browse files

Files changed (1) hide show

README.md +34 -1

README.md CHANGED Viewed

@@ -1,5 +1,38 @@
 ---
 license: cc-by-4.0
 ---
-A SpecTUS model pretrained on synth2_2x4.7M for 2x112k steps.

 ---
 license: cc-by-4.0
+datasets:
+- MS-ML/synth2_2x4.7M
+metrics:
+- accuracy
+library_name: transformers
+tags:
+- mass-spectrometry
+- GC-EI-MS
+- Transformer
+- molecular-structure-elucidation
+- compound-identification
 ---
+A SpecTUS model pretrained on synth2_2x4.7M for 2x112k steps.
+The model is a Transformer-based neural network trained to elucidate molecular structures from GC-EI-MS spectra.
+The model was pretrained on a large dataset of 9.4M synthetic spectra generated from two identical sets of 4.7M
+compounds using the NEIMS [1] and RASSP [2] models.
+We mainly aimed to give the model an understanding of the chemical space of small molecules. The training was
+conducted with a batch size of 128 for 224,000 steps, allowing the model to process each of the 9.4 million spectra approximately three times.
+The entire pretraining process, including control evaluations every 16,000 steps, took 33 hours on a single Nvidia H100 GPU.
+During pretraining, the percentage of correctly reconstructed validation spectra steadily increased, but remained relatively low at the end
+of the stage: 27\% for RASSP-generated spectra, 13\% for NEIMS-generated spectra, and 2\% for NIST spectra. However, 94\% of the generated SMILES
+strings (RASSP, NEIMS) were valid canonical molecules, with 83\% (RASSP), 65\% (NEIMS), and 11\% (NIST) having correct molecular formulas.
+These results suggest that during the pretraining phase, the model successfully learned molecular structure rules and the relationship between atomic
+weight and m/z values, forming a good foundation for subsequent finetuning.
+The full code we used for the data processing, finetuning, evaluation model comparison and more can be found in our GitHub repository [3].
+[1]: https://github.com/brain-research/deep-molecular-massspec
+[2]: https://github.com/thejonaslab/rassp-public
+[3]: !! <TODO>