Instructions to use Hariprasath28/orpheus-3b-multi-gptq-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hariprasath28/orpheus-3b-multi-gptq-8bit with Transformers:

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

pipe = pipeline("text-generation", model="Hariprasath28/orpheus-3b-multi-gptq-8bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Hariprasath28/orpheus-3b-multi-gptq-8bit")
model = AutoModelForCausalLM.from_pretrained("Hariprasath28/orpheus-3b-multi-gptq-8bit")
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

vLLM

How to use Hariprasath28/orpheus-3b-multi-gptq-8bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hariprasath28/orpheus-3b-multi-gptq-8bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hariprasath28/orpheus-3b-multi-gptq-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hariprasath28/orpheus-3b-multi-gptq-8bit

SGLang

How to use Hariprasath28/orpheus-3b-multi-gptq-8bit 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 "Hariprasath28/orpheus-3b-multi-gptq-8bit" \
    --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": "Hariprasath28/orpheus-3b-multi-gptq-8bit",
		"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 "Hariprasath28/orpheus-3b-multi-gptq-8bit" \
        --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": "Hariprasath28/orpheus-3b-multi-gptq-8bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Hariprasath28/orpheus-3b-multi-gptq-8bit with Docker Model Runner:
```
docker model run hf.co/Hariprasath28/orpheus-3b-multi-gptq-8bit
```

Orpheus 3B 8-bit GPTQ

Model Details

Base Model: baseten/orpheus-3b-0.1-ft
Quantization: 8-bit GPTQ
Group Size: 128
Calibration Dataset: canopylabs/zac-sample-dataset (TTS-specific)
Library: auto-gptq

Usage

from auto_gptq import AutoGPTQForCausalLM
from transformers import AutoTokenizer

# Load the quantized model
model = AutoGPTQForCausalLM.from_quantized(
    "Hariprasath28/orpheus-3b-multi-gptq-8bit",
    device="cuda:0",  # or "cpu"
    use_triton=False,
    trust_remote_code=True
)

tokenizer = AutoTokenizer.from_pretrained("Hariprasath28/orpheus-3b-multi-gptq-8bit", trust_remote_code=True)

# Generate TTS tokens
text = "tara: Hello, this is a test of the quantized Orpheus model."
inputs = tokenizer(text, return_tensors="pt").to("cuda:0")

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=100,
        temperature=0.7,
        do_sample=True
    )

generated = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated)

Downloads last month: 1

Model tree for Hariprasath28/orpheus-3b-multi-gptq-8bit

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

canopylabs/orpheus-3b-0.1-pretrained

Finetuned

baseten/orpheus-3b-0.1-ft

Quantized

(3)

this model