Instructions to use OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8")
model = AutoModelForCausalLM.from_pretrained("OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8

SGLang

How to use OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8 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 "OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8" \
    --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": "OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8",
		"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 "OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8" \
        --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": "OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8 with Docker Model Runner:
```
docker model run hf.co/OVHaiLLM/Qwen-Pro-Finance-R-32B-FP8
```

Qwen-Pro-Finance-R-32B-FP8 / LICENSE

gcaillaut

Upload LICENSE with huggingface_hub

f0cc615 verified about 1 year ago

Raw History Blame Contribute Delete

2.65 kB

Copyright (c) 2025 Dragon LLM & l’AGEFI
website: https://dragonllm.ai & https://agefi.fr
Contact: contact@dragonllm.ai
Jurisdiction: France

1. Preamble

This license applies to the model Qwen Pro Finance R 32B ("the Model") released by Dragon LLM. The base model Qwen3-32B is licensed under Apache 2.0. This license covers only the modifications, fine-tuning, weights, documentation, and other contributions provided by Dragon LLM.

2. Authorized Use

The Model is provided strictly for internal research, testing, and evaluation purposes only.

Redistribution of the Model, its derivatives, or access to third parties is prohibited without prior written authorization from Dragon LLM.

3. Commercial Use

Commercial use, including usage for internal production purposes, is prohibited without an explicit written commercial license agreement from Dragon LLM.

To request commercial licensing, contact: contact@dragonllm.ai

4. Restrictions

You agree not to use the Model:

To build competitive foundational AI models

To circumvent export control or compliance regulations

For malicious, harmful, fraudulent, or misleading purposes

To generate financial recommendations presented as legally certified investment advice

For unacceptable and high risk usage as described by the EU AI Act

5. Finance Clause

This model is specialized for financial language modelling. You acknowledge that:

The Model does not provide investment advice, risk recommendations, financial planning, or regulatory guidance

Use in financial workflows must include human supervision and validation

Dragon LLM disclaims all liability for financial losses arising from the use of the Model

You are responsible for ensuring compliance with financial regulations (MiFID II, Basel III/IV, Solvency II, AML/KYC, etc.)

6. Safety & Compliance

You must implement reasonable security and usage safeguards, including:

Content filtering and misuse detection

Audit logging and monitoring

Data privacy and GDPR protection

Bias and hallucination risk mitigation

7. Intellectual Property

Dragon LLM retains full ownership and intellectual property rights to:

Fine-tuning data curation

Training recipes and optimization techniques

Model weight adaptations

8. Warranty Disclaimer

THE MODEL IS PROVIDED "AS IS" WITHOUT WARRANTY OF ANY KIND.

9. Limitation of Liability

IN NO EVENT WILL DRAGON LLM BE LIABLE FOR ANY INDIRECT, INCIDENTAL, OR CONSEQUENTIAL DAMAGES.

10. Governing Law

This agreement is governed by the laws of France. Disputes shall be resolved in the courts of Paris.

	Copyright (c) 2025 Dragon LLM & l’AGEFI
	website: https://dragonllm.ai & https://agefi.fr
	Contact: contact@dragonllm.ai
	Jurisdiction: France

	1. Preamble

	This license applies to the model Qwen Pro Finance R 32B ("the Model") released by Dragon LLM. The base model Qwen3-32B is licensed under Apache 2.0. This license covers only the modifications, fine-tuning, weights, documentation, and other contributions provided by Dragon LLM.

	2. Authorized Use

	The Model is provided strictly for internal research, testing, and evaluation purposes only.

	Redistribution of the Model, its derivatives, or access to third parties is prohibited without prior written authorization from Dragon LLM.

	3. Commercial Use

	Commercial use, including usage for internal production purposes, is prohibited without an explicit written commercial license agreement from Dragon LLM.

	To request commercial licensing, contact: contact@dragonllm.ai

	4. Restrictions

	You agree not to use the Model:

	To build competitive foundational AI models

	To circumvent export control or compliance regulations

	For malicious, harmful, fraudulent, or misleading purposes

	To generate financial recommendations presented as legally certified investment advice

	For unacceptable and high risk usage as described by the EU AI Act

	5. Finance Clause

	This model is specialized for financial language modelling. You acknowledge that:

	The Model does not provide investment advice, risk recommendations, financial planning, or regulatory guidance

	Use in financial workflows must include human supervision and validation

	Dragon LLM disclaims all liability for financial losses arising from the use of the Model

	You are responsible for ensuring compliance with financial regulations (MiFID II, Basel III/IV, Solvency II, AML/KYC, etc.)

	6. Safety & Compliance

	You must implement reasonable security and usage safeguards, including:

	Content filtering and misuse detection

	Audit logging and monitoring

	Data privacy and GDPR protection

	Bias and hallucination risk mitigation

	7. Intellectual Property

	Dragon LLM retains full ownership and intellectual property rights to:

	Fine-tuning data curation

	Training recipes and optimization techniques

	Model weight adaptations

	8. Warranty Disclaimer

	THE MODEL IS PROVIDED "AS IS" WITHOUT WARRANTY OF ANY KIND.

	9. Limitation of Liability

	IN NO EVENT WILL DRAGON LLM BE LIABLE FOR ANY INDIRECT, INCIDENTAL, OR CONSEQUENTIAL DAMAGES.

	10. Governing Law

	This agreement is governed by the laws of France. Disputes shall be resolved in the courts of Paris.