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

Libraries

How to use StarLiu714/GPT-oss-MOF with Transformers:

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

pipe = pipeline("text-generation", model="StarLiu714/GPT-oss-MOF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("StarLiu714/GPT-oss-MOF", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use StarLiu714/GPT-oss-MOF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "StarLiu714/GPT-oss-MOF"
# 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-MOF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/StarLiu714/GPT-oss-MOF

SGLang

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

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

GPT-oss-YearWise

This repository contains the checkpoint-5500 model checkpoint from the YearWise training run.

Model Details

Repository: StarLiu714/GPT-oss-YearWise
Branch: main
Checkpoint source: /Users/starliu/Downloads/train_full-0609/checkpoint-5500/
Primary weights: model.safetensors
License: MIT

Files

The checkpoint includes model weights, tokenizer assets, chat template, optimizer state, scheduler state, RNG state, trainer state, and training arguments.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "StarLiu714/GPT-oss-YearWise"
tokenizer = AutoTokenizer.from_pretrained(repo_id)
model = AutoModelForCausalLM.from_pretrained(repo_id, device_map="auto")

Training and Evaluation

This model card documents the uploaded checkpoint and license. Detailed dataset composition, training configuration, and evaluation metrics should be interpreted from the accompanying training artifacts in this repository where applicable.

License

This model is released under the MIT License.

Downloads last month: -; Downloads are not tracked for this model. How to track

Safetensors

Model size

20B params

Tensor type

F32

BF16