Instructions to use maimai11/woz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maimai11/woz with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("/public/home/202420164005/model/stepfun-ai/Step-Audio2-mini-Think")
model = PeftModel.from_pretrained(base_model, "maimai11/woz")

Transformers

How to use maimai11/woz with Transformers:

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

pipe = pipeline("text-generation", model="maimai11/woz")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("maimai11/woz", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use maimai11/woz with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "maimai11/woz"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "maimai11/woz",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/maimai11/woz

SGLang

How to use maimai11/woz 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 "maimai11/woz" \
    --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": "maimai11/woz",
		"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 "maimai11/woz" \
        --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": "maimai11/woz",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use maimai11/woz with Docker Model Runner:
```
docker model run hf.co/maimai11/woz
```

woz checkpoint-130 LoRA adapter

This repository contains the LoRA adapter exported from the best checkpoint-130 used in the Step-Audio2 DAIC-WOZ Depression experiments.

adapter_model.safetensors
adapter_config.json
additional_config.json
args.json
dev_metrics.json

Intended base model

This adapter is intended to be loaded on top of:

Step-Audio2-mini-Think

The base model is not redistributed in this repository.

Evaluation snapshot

The included dev_metrics.json reports the following result on the project dev split used during this experiment:

accuracy: 0.8571
weighted_f1: 0.8601
macro_f1: 0.8493
f1_yes: 0.8148
tp: 11
tn: 19
fp: 4
fn: 1

Notes

This repository only packages the inference-relevant adapter artifacts.
Optimizer state and other training-only checkpoint files are intentionally excluded.

Downloads last month: 15

maimai11
/

woz

woz checkpoint-130 LoRA adapter

Contents

Intended base model

Evaluation snapshot

Notes