Instructions to use bitext/Mistral-7B-Banking-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bitext/Mistral-7B-Banking-v2 with Transformers:

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

pipe = pipeline("text-generation", model="bitext/Mistral-7B-Banking-v2", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bitext/Mistral-7B-Banking-v2")
model = AutoModelForCausalLM.from_pretrained("bitext/Mistral-7B-Banking-v2", 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 bitext/Mistral-7B-Banking-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bitext/Mistral-7B-Banking-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bitext/Mistral-7B-Banking-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bitext/Mistral-7B-Banking-v2

SGLang

How to use bitext/Mistral-7B-Banking-v2 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 "bitext/Mistral-7B-Banking-v2" \
    --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": "bitext/Mistral-7B-Banking-v2",
		"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 "bitext/Mistral-7B-Banking-v2" \
        --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": "bitext/Mistral-7B-Banking-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bitext/Mistral-7B-Banking-v2 with Docker Model Runner:
```
docker model run hf.co/bitext/Mistral-7B-Banking-v2
```

bitext-innovations commited on Jul 16, 2024

Commit

99a33ef

verified ·

1 Parent(s): f58cac1

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -19,11 +19,13 @@ widget:
 ## Model Description
-"Mistral-7B-Banking-v2" is a specialized adaptation of the [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2), designed to provide precise answers related to general banking queries. This model is fine-tuned to help users with common banking tasks and inquiries.
 ## Intended Use
-- **Recommended applications**: Ideal for deployment in digital banking platforms where quick and accurate customer service responses are needed. It can be integrated into banking chatbots to assist users with transactions, account information, and other banking services.
 - **Out-of-scope**: This model is not suited for non-banking related questions and should not be used for providing health, legal, or critical safety advice.
 ## Usage Example

 ## Model Description
+This model, "Mistral-7B-Banking-v2", is a fine-tuned version of the [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2), specifically tailored for the Banking domain. It is optimized to answer questions and assist users with various banking transactions. It has been trained using hybrid synthetic data generated using our NLP/NLG technology and our automated Data Labeling (DAL) tools.
+The goal of this model is to show that a generic verticalized model makes customization for a final use case much easier. For example, if you are "ACME Bank", you can create your own customized model by using this fine-tuned model and a doing an additional fine-tuning using a small amount of your own data. An overview of this approach can be found at: [From General-Purpose LLMs to Verticalized Enterprise Models](https://www.bitext.com/blog/general-purpose-models-verticalized-enterprise-genai/)
 ## Intended Use
+- **Recommended applications**: This model is designed to be used as the first step in Bitext’s two-step approach to LLM fine-tuning for the creation of chatbots, virtual assistants and copilots for the Banking domain, providing customers with fast and accurate answers about their banking needs.
 - **Out-of-scope**: This model is not suited for non-banking related questions and should not be used for providing health, legal, or critical safety advice.
 ## Usage Example