Instructions to use tlphams/Wizard-Zephyr-Orpo-8x22B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tlphams/Wizard-Zephyr-Orpo-8x22B with Transformers:

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

pipe = pipeline("text-generation", model="tlphams/Wizard-Zephyr-Orpo-8x22B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("tlphams/Wizard-Zephyr-Orpo-8x22B")
model = AutoModelForCausalLM.from_pretrained("tlphams/Wizard-Zephyr-Orpo-8x22B")
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 tlphams/Wizard-Zephyr-Orpo-8x22B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tlphams/Wizard-Zephyr-Orpo-8x22B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tlphams/Wizard-Zephyr-Orpo-8x22B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tlphams/Wizard-Zephyr-Orpo-8x22B

SGLang

How to use tlphams/Wizard-Zephyr-Orpo-8x22B 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 "tlphams/Wizard-Zephyr-Orpo-8x22B" \
    --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": "tlphams/Wizard-Zephyr-Orpo-8x22B",
		"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 "tlphams/Wizard-Zephyr-Orpo-8x22B" \
        --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": "tlphams/Wizard-Zephyr-Orpo-8x22B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tlphams/Wizard-Zephyr-Orpo-8x22B with Docker Model Runner:
```
docker model run hf.co/tlphams/Wizard-Zephyr-Orpo-8x22B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

merge

This is a merge of pre-trained language models created using mergekit.

Merge Details

Models Merged

The following models were included in the merge:

Benchmark results

1. MT-Bench from lmsys

We adapted the code from FastChat to benchmark our model with GPT-4 as a judge. Here is the result

|        | Model                                   | Turn | Score    |
|--------|-----------------------------------------|------|----------|
| First  | tlphams/Wizard-Zephyr-Orpo-8x22B        | 1    | 9.1625   |
|        | mistralai/Mixtral-8x22B-Instruct-v0.1   | 1    | 9.1500   |
| Second | tlphams/Wizard-Zephyr-Orpo-8x22B        | 2    | 8.873418 |
|        | mistralai/Mixtral-8x22B-Instruct-v0.1   | 2    | 8.250000 |
| Average| tlphams/Wizard-Zephyr-Orpo-8x22B        |      | 9.018868 |
|        | mistralai/Mixtral-8x22B-Instruct-v0.1   |      | 8.700000 |

The score is slightly lower than alpindale/WizardLM-2-8x22B, but still higher than GPT-4-0314. Then the research and experimental work still need to continue ^^

Downloads last month: 7

Safetensors

Model size

141B params

Tensor type

BF16

Model tree for tlphams/Wizard-Zephyr-Orpo-8x22B

HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1

alpindale/WizardLM-2-8x22B

Merge model

this model

Finetunes

2 models

Quantizations

2 models