Instructions to use AdaptLLM/finance-LLM-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AdaptLLM/finance-LLM-13B with Transformers:

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

pipe = pipeline("text-generation", model="AdaptLLM/finance-LLM-13B")

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

tokenizer = AutoTokenizer.from_pretrained("AdaptLLM/finance-LLM-13B")
model = AutoModelForCausalLM.from_pretrained("AdaptLLM/finance-LLM-13B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AdaptLLM/finance-LLM-13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AdaptLLM/finance-LLM-13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AdaptLLM/finance-LLM-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AdaptLLM/finance-LLM-13B

SGLang

How to use AdaptLLM/finance-LLM-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 "AdaptLLM/finance-LLM-13B" \
    --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": "AdaptLLM/finance-LLM-13B",
		"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 "AdaptLLM/finance-LLM-13B" \
        --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": "AdaptLLM/finance-LLM-13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AdaptLLM/finance-LLM-13B with Docker Model Runner:
```
docker model run hf.co/AdaptLLM/finance-LLM-13B
```

AdaptLLM commited on Jan 2, 2024

Commit

7ce9bb5

1 Parent(s): 99d48dd

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -56,11 +56,11 @@ MMM Chicago Stock Exchange, Inc.
 Which debt securities are registered to trade on a national securities exchange under 3M's name as of Q2 of 2023?'''
-# NOTE: You do NOT need to follow any prompt templates for the chat model, simply use your input as the prompt
 prompt = user_input
 inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
-outputs = model.generate(input_ids=inputs, max_length=4096)[0]
 answer_start = int(inputs.shape[-1])
 pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True)

 Which debt securities are registered to trade on a national securities exchange under 3M's name as of Q2 of 2023?'''
+# Simply use your input as the prompt
 prompt = user_input
 inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).input_ids.to(model.device)
+outputs = model.generate(input_ids=inputs, max_length=2048)[0]
 answer_start = int(inputs.shape[-1])
 pred = tokenizer.decode(outputs[answer_start:], skip_special_tokens=True)