Instructions to use whaleloops/Mistral-OpenOrca-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use whaleloops/Mistral-OpenOrca-7B with Transformers:

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

pipe = pipeline("text-generation", model="whaleloops/Mistral-OpenOrca-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("whaleloops/Mistral-OpenOrca-7B")
model = AutoModelForCausalLM.from_pretrained("whaleloops/Mistral-OpenOrca-7B")
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 whaleloops/Mistral-OpenOrca-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "whaleloops/Mistral-OpenOrca-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "whaleloops/Mistral-OpenOrca-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/whaleloops/Mistral-OpenOrca-7B

SGLang

How to use whaleloops/Mistral-OpenOrca-7B 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 "whaleloops/Mistral-OpenOrca-7B" \
    --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": "whaleloops/Mistral-OpenOrca-7B",
		"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 "whaleloops/Mistral-OpenOrca-7B" \
        --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": "whaleloops/Mistral-OpenOrca-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use whaleloops/Mistral-OpenOrca-7B with Docker Model Runner:
```
docker model run hf.co/whaleloops/Mistral-OpenOrca-7B
```

This is a replicate of https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca

But in safetensor format

Prompt Template

To use the prompt for further training and inference, please use OpenAI's Chat Markup Language (ChatML) format, with <|im_start|> and <|im_end|> tokens added to support this.

This means that, e.g., in oobabooga the "MPT-Chat" instruction template should work, as it also uses ChatML.

This formatting is also available via a pre-defined Transformers chat template, which means that lists of messages can be formatted for you with the apply_chat_template() method:

chat = [
  {"role": "system", "content": "You are MistralOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers!"}
  {"role": "user", "content": "How are you?"},
  {"role": "assistant", "content": "I am doing well!"},
  {"role": "user", "content": "Please tell me about how mistral winds have attracted super-orcas."},
]
tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)

which will yield:

<|im_start|>system
You are MistralOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers!
<|im_end|>
<|im_start|>user
How are you?<|im_end|>
<|im_start|>assistant
I am doing well!<|im_end|>
<|im_start|>user
Please tell me about how mistral winds have attracted super-orcas.<|im_end|>
<|im_start|>assistant

If you use tokenize=True and return_tensors="pt" instead, then you will get a tokenized and formatted conversation ready to pass to model.generate().

Inference

See this notebook for inference details.

Note that you need the development snapshot of Transformers currently, as support for Mistral hasn't been released into PyPI yet:

pip install git+https://github.com/huggingface/transformers

Downloads last month: 6

Safetensors

Model size

7B params

Tensor type

BF16