Instructions to use orangetin/OpenHermes-Mixtral-8x7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use orangetin/OpenHermes-Mixtral-8x7B with Transformers:

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

pipe = pipeline("text-generation", model="orangetin/OpenHermes-Mixtral-8x7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("orangetin/OpenHermes-Mixtral-8x7B")
model = AutoModelForCausalLM.from_pretrained("orangetin/OpenHermes-Mixtral-8x7B", 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 orangetin/OpenHermes-Mixtral-8x7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "orangetin/OpenHermes-Mixtral-8x7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "orangetin/OpenHermes-Mixtral-8x7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/orangetin/OpenHermes-Mixtral-8x7B

SGLang

How to use orangetin/OpenHermes-Mixtral-8x7B 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 "orangetin/OpenHermes-Mixtral-8x7B" \
    --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": "orangetin/OpenHermes-Mixtral-8x7B",
		"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 "orangetin/OpenHermes-Mixtral-8x7B" \
        --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": "orangetin/OpenHermes-Mixtral-8x7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use orangetin/OpenHermes-Mixtral-8x7B with Docker Model Runner:
```
docker model run hf.co/orangetin/OpenHermes-Mixtral-8x7B
```

orangetin commited on Apr 13, 2024

Commit

0b53f5f

verified ·

1 Parent(s): 8e01116

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -12

README.md CHANGED Viewed

@@ -28,18 +28,6 @@ Huge thank you to [Teknium](https://huggingface.co/datasets/teknium) for open-so
 This model was trained on the [OpenHermes dataset](https://huggingface.co/datasets/teknium/openhermes) for 3 epochs
-## [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
-Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_orangetin__OpenHermes-Mixtral-8x7B)
- | Metric                | Value                     |
-|-----------------------|---------------------------|
-| Avg.                  | 65.27   |
-| ARC (25-shot)         | 63.91          |
-| HellaSwag (10-shot)   | 84.14    |
-| MMLU (5-shot)         | 64.29         |
-| TruthfulQA (0-shot)   | 59.53   |
-| Winogrande (5-shot)   | 74.03   |
-| GSM8K (5-shot)        | 45.72        |
 # Prompt Format


28
29	This model was trained on the [OpenHermes dataset](https://huggingface.co/datasets/teknium/openhermes) for 3 epochs
30












31
32	# Prompt Format
33