Instructions to use yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full with Transformers:

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

pipe = pipeline("text-generation", model="yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full

SGLang

How to use yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full 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 "yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full" \
    --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": "yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full",
		"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 "yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full" \
        --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": "yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full with Docker Model Runner:
```
docker model run hf.co/yigagilbert/stepaudio2-mini-luganda-english-bidirectional-s2st-full
```

stepaudio2-mini-luganda-english-bidirectional-s2st-full / config.json

yigagilbert

Upload merged bidirectional Step-Audio-2-mini Luganda-English model

8eb4145 verified 4 months ago

Raw History Blame Contribute Delete

2.04 kB

	{
	"architectures": [
	"StepAudio2ForCausalLM"
	],
	"audio_encoder_config": {
	"adapter_stride": 2,
	"kernel_size": 3,
	"llm_dim": 3584,
	"model_type": "step_audio_2_encoder",
	"n_audio_ctx": 1500,
	"n_audio_head": 20,
	"n_audio_layer": 32,
	"n_audio_state": 1280,
	"n_codebook_size": 4096,
	"n_mels": 128
	},
	"auto_map": {
	"AutoConfig": "configuration_step_audio_2.StepAudio2Config",
	"AutoModelForCausalLM": "modeling_step_audio_2.StepAudio2ForCausalLM"
	},
	"dtype": "bfloat16",
	"max_window_layers": null,
	"model_type": "step_audio_2",
	"sliding_window": 2048,
	"text_config": {
	"architectures": [
	"Qwen2ForCausalLM"
	],
	"attention_dropout": 0.0,
	"dtype": "bfloat16",
	"hidden_act": "silu",
	"hidden_size": 3584,
	"initializer_range": 0.02,
	"intermediate_size": 18944,
	"layer_types": [
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"max_position_embeddings": 16384,
	"max_window_layers": 28,
	"model_type": "qwen2",
	"num_attention_heads": 28,
	"num_hidden_layers": 28,
	"num_key_value_heads": 4,
	"rms_norm_eps": 1e-06,
	"rope_scaling": null,
	"rope_theta": 1000000.0,
	"sliding_window": null,
	"use_cache": true,
	"use_sliding_window": false,
	"vocab_size": 158720
	},
	"tie_word_embeddings": false,
	"transformers_version": "4.57.6",
	"use_sliding_window": false
	}