Instructions to use YaTharThShaRma999/orpheus_model-4bit-bnb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YaTharThShaRma999/orpheus_model-4bit-bnb with Transformers:

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

pipe = pipeline("text-generation", model="YaTharThShaRma999/orpheus_model-4bit-bnb")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("YaTharThShaRma999/orpheus_model-4bit-bnb")
model = AutoModelForCausalLM.from_pretrained("YaTharThShaRma999/orpheus_model-4bit-bnb", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YaTharThShaRma999/orpheus_model-4bit-bnb with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YaTharThShaRma999/orpheus_model-4bit-bnb"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YaTharThShaRma999/orpheus_model-4bit-bnb",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/YaTharThShaRma999/orpheus_model-4bit-bnb

SGLang

How to use YaTharThShaRma999/orpheus_model-4bit-bnb 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 "YaTharThShaRma999/orpheus_model-4bit-bnb" \
    --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": "YaTharThShaRma999/orpheus_model-4bit-bnb",
		"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 "YaTharThShaRma999/orpheus_model-4bit-bnb" \
        --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": "YaTharThShaRma999/orpheus_model-4bit-bnb",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use YaTharThShaRma999/orpheus_model-4bit-bnb with Docker Model Runner:
```
docker model run hf.co/YaTharThShaRma999/orpheus_model-4bit-bnb
```

Install orpheus tts: https://github.com/canopyai/Orpheus-Speech-PyPi

Load model:

from orpheus_tts import OrpheusModel
import wave
import time

gpu_memory_utilization = 0.5 ## Change according to how much vram you have, 0.5 is a decent spot


model = OrpheusModel(model_name ="YaTharThShaRma999/orpheus_model-4bit-bnb", max_seq_len_to_capture=4096, quantization="bitsandbytes", gpu_memory_utilization=gpu_memory_utilization)
prompt = '''So um Orpheus seems pretty interesting, doesn't it? Cool right?'''

start_time = time.monotonic()
syn_tokens = model.generate_speech(
   prompt=prompt,
   voice="tara",
   )

with wave.open("output.wav", "wb") as wf:
   wf.setnchannels(1)
   wf.setsampwidth(2)
   wf.setframerate(24000)

   total_frames = 0
   chunk_counter = 0
   for audio_chunk in syn_tokens: # output streaming
      chunk_counter += 1
      frame_count = len(audio_chunk) // (wf.getsampwidth() * wf.getnchannels())
      total_frames += frame_count
      wf.writeframes(audio_chunk)
   duration = total_frames / wf.getframerate()

   end_time = time.monotonic()
   print(f"It took {end_time - start_time} seconds to generate {duration:.2f} seconds of audio")

Downloads last month: 7

Safetensors

Model size

3B params

Tensor type

F32

F16

Model tree for YaTharThShaRma999/orpheus_model-4bit-bnb

Adapters

1 model