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

Libraries

How to use FloatinggOnion/orpheus_lora_yor with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("FloatinggOnion/orpheus_finetune_16bit")
model = PeftModel.from_pretrained(base_model, "FloatinggOnion/orpheus_lora_yor")

Transformers

How to use FloatinggOnion/orpheus_lora_yor with Transformers:

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

pipe = pipeline("text-generation", model="FloatinggOnion/orpheus_lora_yor")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("FloatinggOnion/orpheus_lora_yor", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FloatinggOnion/orpheus_lora_yor with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/FloatinggOnion/orpheus_lora_yor

SGLang

How to use FloatinggOnion/orpheus_lora_yor 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 "FloatinggOnion/orpheus_lora_yor" \
    --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": "FloatinggOnion/orpheus_lora_yor",
		"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 "FloatinggOnion/orpheus_lora_yor" \
        --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": "FloatinggOnion/orpheus_lora_yor",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use FloatinggOnion/orpheus_lora_yor with Docker Model Runner:
```
docker model run hf.co/FloatinggOnion/orpheus_lora_yor
```

FloatinggOnion commited on May 9

Commit

8b31d25

verified ·

1 Parent(s): 0edf65f

trained on 20k samples (Trained with Unsloth)

Browse files

Files changed (2) hide show

adapter_config.json +1 -1
adapter_model.safetensors +1 -1

adapter_config.json CHANGED Viewed

@@ -7,7 +7,7 @@
     "parent_library": "transformers.models.llama.modeling_llama",
     "unsloth_fixed": true
   },
-  "base_model_name_or_path": "unsloth/orpheus-3b-0.1-ft",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,

     "parent_library": "transformers.models.llama.modeling_llama",
     "unsloth_fixed": true
   },
+  "base_model_name_or_path": "FloatinggOnion/orpheus_finetune_16bit",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77663daf63e244845a7285f9cf705fdbeff64f8c45b0aa4d036012c2ebff207f
 size 389074464

 version https://git-lfs.github.com/spec/v1
+oid sha256:891e9f3b89d3b253776708670e6a2e1bbb23c7b24f023530f9b9f2a9cc7290b2
 size 389074464