Instructions to use xieyuquan/Optimus3-32B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xieyuquan/Optimus3-32B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="xieyuquan/Optimus3-32B-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForSeq2SeqLM
model = AutoModelForSeq2SeqLM.from_pretrained("xieyuquan/Optimus3-32B-SFT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use xieyuquan/Optimus3-32B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xieyuquan/Optimus3-32B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xieyuquan/Optimus3-32B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xieyuquan/Optimus3-32B-SFT

SGLang

How to use xieyuquan/Optimus3-32B-SFT 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 "xieyuquan/Optimus3-32B-SFT" \
    --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": "xieyuquan/Optimus3-32B-SFT",
		"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 "xieyuquan/Optimus3-32B-SFT" \
        --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": "xieyuquan/Optimus3-32B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xieyuquan/Optimus3-32B-SFT with Docker Model Runner:
```
docker model run hf.co/xieyuquan/Optimus3-32B-SFT
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 32
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 512
total_eval_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.25
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
1.598	0.1182	30	1.4674
0.9568	0.2365	60	0.9714
0.878	0.3547	90	0.8730
0.8978	0.4729	120	0.8298
0.7648	0.5911	150	0.7882
0.7389	0.7094	180	0.7603
0.7876	0.8276	210	0.7392
0.7791	0.9458	240	0.7206
0.6523	1.0631	270	0.7225
0.6282	1.1813	300	0.7122
0.5979	1.2995	330	0.7028
0.594	1.4177	360	0.6956
0.6003	1.5360	390	0.6844
0.5274	1.6542	420	0.6777
0.5692	1.7724	450	0.6741
0.5754	1.8906	480	0.6712

Framework versions

Transformers 4.51.3
Pytorch 2.6.0+cu118
Datasets 3.5.0
Tokenizers 0.21.1

Downloads last month: -

Safetensors

Model size

40B params

Tensor type

BF16