Instructions to use StarLiu714/GPT-oss-MOFinder-enriched with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use StarLiu714/GPT-oss-MOFinder-enriched with Transformers:

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

pipe = pipeline("text-generation", model="StarLiu714/GPT-oss-MOFinder-enriched")
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("StarLiu714/GPT-oss-MOFinder-enriched")
model = AutoModelForCausalLM.from_pretrained("StarLiu714/GPT-oss-MOFinder-enriched", 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 StarLiu714/GPT-oss-MOFinder-enriched with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "StarLiu714/GPT-oss-MOFinder-enriched"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "StarLiu714/GPT-oss-MOFinder-enriched",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/StarLiu714/GPT-oss-MOFinder-enriched

SGLang

How to use StarLiu714/GPT-oss-MOFinder-enriched 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 "StarLiu714/GPT-oss-MOFinder-enriched" \
    --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": "StarLiu714/GPT-oss-MOFinder-enriched",
		"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 "StarLiu714/GPT-oss-MOFinder-enriched" \
        --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": "StarLiu714/GPT-oss-MOFinder-enriched",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use StarLiu714/GPT-oss-MOFinder-enriched with Docker Model Runner:
```
docker model run hf.co/StarLiu714/GPT-oss-MOFinder-enriched
```

GPT-oss-MOFinder-enriched: chemical info expansion

This repository gives the attempts expanding our default assembly, 8-field chemical reasoning, to more wet-lab procedural details feeding a GPT base model. We reports the performance of finetuned GPT opensource models with 9 or even longer prompting on MOF synthesizability task.

Result

Train fields	Inference	Test size	Accuracy	Precision
add "stirring" field	Holdout	1320P+ 1275N	0.8347	0.8113
	22 questions	11P + 11N	18/22	0.7333
add "vessel_type, vessel_volume_mL, and agitation" fields	Holdout	1320P+ 1275N	0.8324	0.8310
	22 questions	11P + 11N	18/22	0.7333
default 8-field MOFinder	Holdout	1320P+ 1275N	0.8301	0.8273
	22 questions	11P + 11N	20/22	0.8462

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "GPT-oss-MOFinder-enriched"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

To go throught the quick start details for reprduction, see the official released MOFinder main checkpoint which is well-trained on full-field PN data.

Citation and license

When using these weights, cite MOFinder, identify StarLiu714/GPT-oss-MOF and the Hub revision used, and reference the GPT-oss-20B base model. This release is licensed under the GNU General Public License v3.0; see LICENSE. The underlying GPT-oss-20B model retains its upstream Apache-2.0 license, reproduced in LICENSE.base-model. This release includes MOF fine-tuning changes merged into the base model and a BF16 weight export. MOFinder codebase is separately licensed under MIT.

Downloads last month: 215

Safetensors

Model size

21B params

Tensor type

BF16

Model tree for StarLiu714/GPT-oss-MOFinder-enriched

Base model

openai/gpt-oss-20b

Finetuned

(566)

this model

Collection including StarLiu714/GPT-oss-MOFinder-enriched

MOFinder

Collection

MOF synthesis specific finetuned GPT-oss-20B model, with its ablations and time-series experiment assets. • 5 items • Updated 16 days ago