Instructions to use davzoku/finqa_expert_3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use davzoku/finqa_expert_3b with Transformers:

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

pipe = pipeline("text-generation", model="davzoku/finqa_expert_3b")
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("davzoku/finqa_expert_3b")
model = AutoModelForCausalLM.from_pretrained("davzoku/finqa_expert_3b", 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 davzoku/finqa_expert_3b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "davzoku/finqa_expert_3b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davzoku/finqa_expert_3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/davzoku/finqa_expert_3b

SGLang

How to use davzoku/finqa_expert_3b 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 "davzoku/finqa_expert_3b" \
    --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": "davzoku/finqa_expert_3b",
		"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 "davzoku/finqa_expert_3b" \
        --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": "davzoku/finqa_expert_3b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use davzoku/finqa_expert_3b with Docker Model Runner:
```
docker model run hf.co/davzoku/finqa_expert_3b
```

🫐🥫 finqa_expert_3b

logo

Model Details

This model is a domain-specific expert model for Moecule family of MoE models.

It is part of Moecule Ingredients and all relevant expert models, LoRA adapters, and datasets can be found there.

Additional Information

QLoRA 4-bit fine-tuning with Unsloth
Base Model: unsloth/llama-3.2-3b-Instruct

The Team

CHOCK Wan Kee
Farlin Deva Binusha DEVASUGIN MERLISUGITHA
GOH Bao Sheng
Jessica LEK Si Jia
Sinha KHUSHI
TENG Kok Wai (Walter)

References

Downloads last month: 10

Safetensors

Model size

3B params

Tensor type

F16

Dataset used to train davzoku/finqa_expert_3b

Collection including davzoku/finqa_expert_3b

🫐🥫Moecule Ingredients

Collection

Collection of Expert Models, LoRa adapters and Datasets used to create Moecule models • 24 items • Updated Mar 25, 2025 • 1