Instructions to use bhushan1729/orpheus-3b-stage3-emotion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bhushan1729/orpheus-3b-stage3-emotion with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/orpheus-3b-0.1-ft")
model = PeftModel.from_pretrained(base_model, "bhushan1729/orpheus-3b-stage3-emotion")

Transformers

How to use bhushan1729/orpheus-3b-stage3-emotion with Transformers:

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

pipe = pipeline("text-generation", model="bhushan1729/orpheus-3b-stage3-emotion")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bhushan1729/orpheus-3b-stage3-emotion", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bhushan1729/orpheus-3b-stage3-emotion with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bhushan1729/orpheus-3b-stage3-emotion"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bhushan1729/orpheus-3b-stage3-emotion",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bhushan1729/orpheus-3b-stage3-emotion

SGLang

How to use bhushan1729/orpheus-3b-stage3-emotion 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 "bhushan1729/orpheus-3b-stage3-emotion" \
    --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": "bhushan1729/orpheus-3b-stage3-emotion",
		"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 "bhushan1729/orpheus-3b-stage3-emotion" \
        --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": "bhushan1729/orpheus-3b-stage3-emotion",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use bhushan1729/orpheus-3b-stage3-emotion with Docker Model Runner:
```
docker model run hf.co/bhushan1729/orpheus-3b-stage3-emotion
```

orpheus-3b-stage3-emotion

This model is a fine-tuned version of unsloth/orpheus-3b-0.1-ft on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 5.6753

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: 5e-05
train_batch_size: 2
eval_batch_size: 1
seed: 1242
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 2
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
5.5569	0.5405	5	5.7018
5.5521	1.0	10	5.6959
5.5504	1.5405	15	5.6865
5.5622	2.0	20	5.6753

Framework versions

PEFT 0.20.0
Transformers 4.56.2
Pytorch 2.10.0+cu128
Datasets 3.6.0
Tokenizers 0.22.2

Downloads last month: 22

Model tree for bhushan1729/orpheus-3b-stage3-emotion

Base model

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

Finetuned

canopylabs/orpheus-3b-0.1-pretrained

Finetuned

canopylabs/orpheus-3b-0.1-ft

Finetuned

unsloth/orpheus-3b-0.1-ft

Adapter

(46)

this model