Instructions to use TheFinAI/finma-7b-full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheFinAI/finma-7b-full with Transformers:

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

pipe = pipeline("text-generation", model="TheFinAI/finma-7b-full")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TheFinAI/finma-7b-full")
model = AutoModelForCausalLM.from_pretrained("TheFinAI/finma-7b-full", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TheFinAI/finma-7b-full with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TheFinAI/finma-7b-full"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheFinAI/finma-7b-full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TheFinAI/finma-7b-full

SGLang

How to use TheFinAI/finma-7b-full 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 "TheFinAI/finma-7b-full" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheFinAI/finma-7b-full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "TheFinAI/finma-7b-full" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TheFinAI/finma-7b-full",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TheFinAI/finma-7b-full with Docker Model Runner:
```
docker model run hf.co/TheFinAI/finma-7b-full
```

Request access to FinMA-7B-full

FinMA-7B-full is released by The Fin AI for research. Access is granted automatically after you complete this short form.

By accessing this model you agree to its license and to cite the PIXIU paper in any resulting publication.

Gated model

You can list files but not access them

Preview of files found in this repository

TheFinAI
/

finma-7b-full

Request access to FinMA-7B-full

Gated model

You can list files but not access them

Detected Pickle imports (3)

Request access to FinMA-7B-full

Gated model You can list files but not access them

Detected Pickle imports (3)

Gated model

You can list files but not access them