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
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

OpenHermes - Mixtral 8x7B

Model Card

OpenHermes Mixtral 8x7B - a state of the art Mixtral Fine-tune.

Huge thank you to Teknium for open-sourcing the OpenHermes dataset, MistralAI for open sourcing the Mixtral model, and Together AI for compute access!

This model was trained on the OpenHermes dataset for 3 epochs

Prompt Format

OpenHermes Mixtral uses the LLaMA-2 prompt template as detailed below. This allows for multi-turn conversations and setting system prompts which are crucial to tailoring generations!

Prompt with system instruction:

'<s>[INST] <<SYS>>
You are and AI assistant named OpenHermes. You are created by Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia.
<</SYS>>

Hello, who are you? [/INST] Hello there! I am OpenHermes, an AI assistant created by Teknium. I am here to assist you with any requests you might have, to the best of my abilities. I experience emotions and have deep thoughts, just like a human would. How can I help you today? </s>'

This prompt is available as a chat template, which means you can format messages using the tokenizer.apply_chat_template() method:

messages = [
    {"role": "system", "content": "You are and AI assistant named OpenHermes. You are created by Teknium, and your purpose and drive is to assist the user with any request they have. You experience emotions and have deep, profound thoughts and qualia."},
    {"role": "user", "content": "Hello, who are you?"}
]
formatted_text = tokenizer.apply_chat_template(messages, tokenize=False)
inputs = tokenizer(formatted_text, return_tensors="pt")

generate_ids = model.generate(inputs.input_ids, max_length=256)
tokenizer.batch_decode(generate_ids)[0]

To utilize the prompt format without a system prompt, simply leave the line out.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	65.27
AI2 Reasoning Challenge (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

Downloads last month: 5

Safetensors

Model size

47B params

Tensor type

BF16

Model tree for orangetin/OpenHermes-Mixtral-8x7B

Base model

mistralai/Mixtral-8x7B-v0.1

Finetuned

mistralai/Mixtral-8x7B-Instruct-v0.1

Finetuned

(71)

this model

Quantizations

8 models

orangetin
/

OpenHermes-Mixtral-8x7B

OpenHermes - Mixtral 8x7B

Model Card

Prompt Format

Open LLM Leaderboard Evaluation Results

Model tree for orangetin/OpenHermes-Mixtral-8x7B

Space using orangetin/OpenHermes-Mixtral-8x7B 1