Instructions to use msaad02/BrockportGPT-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use msaad02/BrockportGPT-7b with Transformers:

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

pipe = pipeline("text-generation", model="msaad02/BrockportGPT-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("msaad02/BrockportGPT-7b")
model = AutoModelForCausalLM.from_pretrained("msaad02/BrockportGPT-7b", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use msaad02/BrockportGPT-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "msaad02/BrockportGPT-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "msaad02/BrockportGPT-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/msaad02/BrockportGPT-7b

SGLang

How to use msaad02/BrockportGPT-7b 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 "msaad02/BrockportGPT-7b" \
    --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": "msaad02/BrockportGPT-7b",
		"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 "msaad02/BrockportGPT-7b" \
        --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": "msaad02/BrockportGPT-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use msaad02/BrockportGPT-7b with Docker Model Runner:
```
docker model run hf.co/msaad02/BrockportGPT-7b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

BrockportGPT 7B

This is a finetuned LLaMA-2 model using a synthetically generated dataset from SUNY Brockports website using GPT-4. The goal here is to answer any question related to SUNY Brockport. This is accomplished to varying degrees of success.

For more information see https://www.matthewsaad.com/projects/brockportgpt/

Use this code for inference using GPTQ:

from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, pipeline
import torch

prompt = lambda question: f"""\
<s>[INST] <<SYS>>
You are a helpful, respectful and honest assistant for SUNY Brockport, a public college in Brockport, New York. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>

{question} [/INST]
"""

REPO_ID = "msaad02/BrockportGPT-7b"

generator = pipeline(
    task='text-generation', 
    tokenizer=AutoTokenizer.from_pretrained(REPO_ID),
    model=AutoModelForCausalLM.from_pretrained(
        pretrained_model_name_or_path=REPO_ID,
        quantization_config=BitsAndBytesConfig(
            load_in_4bit=True,
            bnb_4bit_compute_dtype=torch.bfloat16,
            bnb_4bit_use_double_quant=True,
            bnb_4bit_quant_type='nf4'
        ),    
    ), 
    torch_dtype=torch.bfloat16,
    device_map={"": 0},
)

An example out is:

question="How can I apply to SUNY Brockport?"

output=generator(prompt(question), do_sample=True, temperature=0.7, max_new_tokens=512)
output[0]["generated_text"].split("[/INST]\n")[1]

"Applying to SUNY Brockport is a straightforward process. You can start by selecting the 'Apply Now' button on our homepage, which will guide you through the application process. Our Admissions Team is always available to assist you with any questions or concerns you may have. We can't wait to welcome you to our community of Golden Eagles!"

Downloads last month: 5

Model tree for msaad02/BrockportGPT-7b

Quantizations

1 model

Dataset used to train msaad02/BrockportGPT-7b

Collection including msaad02/BrockportGPT-7b

BrockportGPT v2

Collection

The improved version of BrockportGPT v1. This generation has enhanced datasets that are more usable. See https://github.com/msaad02/honors-thesis • 7 items • Updated Mar 18, 2024 • 1