Instructions to use pszemraj/Ballpark-Trivia-XL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pszemraj/Ballpark-Trivia-XL with Transformers:

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

pipe = pipeline("text-generation", model="pszemraj/Ballpark-Trivia-XL")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pszemraj/Ballpark-Trivia-XL")
model = AutoModelForCausalLM.from_pretrained("pszemraj/Ballpark-Trivia-XL")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pszemraj/Ballpark-Trivia-XL with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/pszemraj/Ballpark-Trivia-XL

SGLang

How to use pszemraj/Ballpark-Trivia-XL 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 "pszemraj/Ballpark-Trivia-XL" \
    --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": "pszemraj/Ballpark-Trivia-XL",
		"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 "pszemraj/Ballpark-Trivia-XL" \
        --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": "pszemraj/Ballpark-Trivia-XL",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pszemraj/Ballpark-Trivia-XL with Docker Model Runner:
```
docker model run hf.co/pszemraj/Ballpark-Trivia-XL
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Ballpark Trivia: Size XL

Check out a demo on HF Spaces here.

Are you frequently asked google-able Trivia questions and annoyed by it? Well, this is the model for you! Ballpark Trivia Bot answers any trivia question with something that sounds plausible but is probably not 100% correct. One might say.. the answers are in the right ballpark.

This is by far the largest model trained and should be more credible in its answers or at least able to handle more kinds of questions.

what is the temperature of dry ice in kelvin

person beta: 
194.65 K

Training

This text gen model is a GPT-2 ~1.5 B Parameter Size XL Model, first trained on Wizard of Wikipedia for 40k steps (33/36 layers frozen for the fine-tuning), and then subsequently trained for 40k steps on a parsed variant of Natural Questions(then 34/36 layers frozen for the second fine-tuning) to accidentally create this model.

Note that because the model was originally trained for use in a chatbot application, it uses a named conversation dialogue structure, i.e. the questions are asked by person alpha, and responded to by person beta. Even if you don't specify person alpha in the prompt, it hopefully responds to any question.

Example Prompt

the default examples are not great
you can type in any trivia question or delete the example and write what or when in there, and it will generate the rest of the trivia question and the answer!

Downloads last month: 10

Safetensors

Model size

2B params

Tensor type

F32

Model tree for pszemraj/Ballpark-Trivia-XL

Quantizations

2 models