Instructions to use ceadar-ie/FinanceConnect-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ceadar-ie/FinanceConnect-13B with Transformers:

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

pipe = pipeline("text-generation", model="ceadar-ie/FinanceConnect-13B")
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("ceadar-ie/FinanceConnect-13B")
model = AutoModelForCausalLM.from_pretrained("ceadar-ie/FinanceConnect-13B", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ceadar-ie/FinanceConnect-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ceadar-ie/FinanceConnect-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ceadar-ie/FinanceConnect-13B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ceadar-ie/FinanceConnect-13B

SGLang

How to use ceadar-ie/FinanceConnect-13B 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 "ceadar-ie/FinanceConnect-13B" \
    --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": "ceadar-ie/FinanceConnect-13B",
		"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 "ceadar-ie/FinanceConnect-13B" \
        --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": "ceadar-ie/FinanceConnect-13B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ceadar-ie/FinanceConnect-13B with Docker Model Runner:
```
docker model run hf.co/ceadar-ie/FinanceConnect-13B
```

ceadar-ie commited on Dec 11, 2023

Commit

2445450

1 Parent(s): e7f27d3

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -0

README.md CHANGED Viewed

@@ -47,6 +47,14 @@ Drawing strength from the FinTalk-19k and Alpaca dataset, a curated collection f
 | FPB | 51.1 | 57.2 |
 | **Cost**| **$2.67 Million** | **$27** |
 ## Model Usage
 Experience the capabilities of the FinanceConnect model through a well-structured Python interface. To kick-start your exploration, follow the steps and snippets given below:

 | FPB | 51.1 | 57.2 |
 | **Cost**| **$2.67 Million** | **$27** |
+| **Benchmark** | **FinanceConnect 13B** |
+|--------------|--------------
+| MMLU | 52.08 |
+| ARC | 55.12 |
+| HellaSwag | 77.73 |
+| TruthfulQA | 38.80 |
+| Winogrande | 71.82 |
+| GSM8K | 1.6 |
 ## Model Usage
 Experience the capabilities of the FinanceConnect model through a well-structured Python interface. To kick-start your exploration, follow the steps and snippets given below: