Instructions to use rohanbalkondekar/MistralOrca-7B-BankingSupport with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rohanbalkondekar/MistralOrca-7B-BankingSupport with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rohanbalkondekar/MistralOrca-7B-BankingSupport")
model = AutoModelForCausalLM.from_pretrained("rohanbalkondekar/MistralOrca-7B-BankingSupport")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rohanbalkondekar/MistralOrca-7B-BankingSupport with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/rohanbalkondekar/MistralOrca-7B-BankingSupport

SGLang

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

Docker Model Runner
How to use rohanbalkondekar/MistralOrca-7B-BankingSupport with Docker Model Runner:
```
docker model run hf.co/rohanbalkondekar/MistralOrca-7B-BankingSupport
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

The Model Generates JSON for the following Five Actions

// When the user asks for account balance without specifying the account type
// Example: What is my current account balance?
{"action": "account_balance", "type": "default"}

// When the user asks for the account balance in his checking account
// Example: What's the balance in my checking account?
{"action": "account_balance", "type": "checking"}

// When the user asks for the account balance in his savings account
// Example: What's the balance in my savings account?
{"action": "account_balance", "type": "savings"}

// When the user asks for an account statement without specifying any date range
// Example: I need my account statement.
{"action": "account_statement", "type": "default"}

// When the user asks for an account statement with a specified date range
// Example: Show me my statement from September 10th, 2023 to September 15th, 2023.
{"action": "account_statement", "type": "custom", "start_date": "10/09/2023", "end_date": "15/09/2023" }

Downloads last month: 7