Instructions to use richardburleigh/SuperQA-7B-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use richardburleigh/SuperQA-7B-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="richardburleigh/SuperQA-7B-v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("richardburleigh/SuperQA-7B-v0.1")
model = AutoModelForMultimodalLM.from_pretrained("richardburleigh/SuperQA-7B-v0.1")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use richardburleigh/SuperQA-7B-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "richardburleigh/SuperQA-7B-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "richardburleigh/SuperQA-7B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/richardburleigh/SuperQA-7B-v0.1

SGLang

How to use richardburleigh/SuperQA-7B-v0.1 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 "richardburleigh/SuperQA-7B-v0.1" \
    --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": "richardburleigh/SuperQA-7B-v0.1",
		"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 "richardburleigh/SuperQA-7B-v0.1" \
        --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": "richardburleigh/SuperQA-7B-v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use richardburleigh/SuperQA-7B-v0.1 with Docker Model Runner:
```
docker model run hf.co/richardburleigh/SuperQA-7B-v0.1
```

Model Card for SuperQA-7B

This model is a fine-tuned version of Mistral-7B-v0.1, specifically designed for Question Answering (QA) tasks. It has been trained on a private dataset comprising 120,000 document, question, and answer pairs.

To my knowledge, this is the most capable 7B model for Retrieval Augmented Generation (RAG) tasks.

SuperQA responds in Markdown format.

Prompt Format

This model was trained only with the following prompt:

<s>[INST] Respond with a detailed and relevant answer to my question using only information from the provided context.

<|context|>
<|doc|>
{Your document}
<|/doc|>
<|/context|>

<|question|>{Your question?}<|/question|> [/INST]

Limitations

While the model is designed to be accurate and relevant, its performance is contingent on the quality and relevance of the provided context. Answers may be less accurate if the context is insufficient or not directly related to the question. Additionally, the model's training on a specific dataset may limit its effectiveness in answering questions outside the scope of the training data.

Disclaimer

This model is provided as-is without any guarantees of performance or accuracy. Users should not rely solely on this model for critical decisions or interpretations. The developers of this model are not responsible for any direct or indirect consequences arising from its use. It is the responsibility of the user to ensure that the model's output is appropriate for their specific context and requirements.

Downloads last month: 4

Safetensors

Model size

7B params

Tensor type

F16