Instructions to use jtatman/zephyr-3b-gravityfalls with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jtatman/zephyr-3b-gravityfalls with Transformers:

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

pipe = pipeline("text-generation", model="jtatman/zephyr-3b-gravityfalls", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("jtatman/zephyr-3b-gravityfalls", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use jtatman/zephyr-3b-gravityfalls with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jtatman/zephyr-3b-gravityfalls"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jtatman/zephyr-3b-gravityfalls",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jtatman/zephyr-3b-gravityfalls

SGLang

How to use jtatman/zephyr-3b-gravityfalls 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 "jtatman/zephyr-3b-gravityfalls" \
    --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": "jtatman/zephyr-3b-gravityfalls",
		"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 "jtatman/zephyr-3b-gravityfalls" \
        --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": "jtatman/zephyr-3b-gravityfalls",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jtatman/zephyr-3b-gravityfalls with Docker Model Runner:
```
docker model run hf.co/jtatman/zephyr-3b-gravityfalls
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Model Card for zephyr-3b-gravityfalls

This model is finetuned using episode scripts from gravity falls, a favorite of my own progeny.

Model Details

From what I remember, it's not very well tuned, and definately was an early project - to my detriment I can't find the original notebook and training scripts. In fact, this was before I became a huge fan of using WandB for tracking, so that's my excuse, and I'm sticking with it.

Model Description

Purely for fun, with no real practical usage.

Developed by: TTML
Funded by [optional]: Useless energy
Shared by [optional]: jtatman
Model type: zephyr 7b chat
Language(s) (NLP): English
License: Apache, assuming this is ok with the creators of a truly wonderful and creative show.
Finetuned from model [optional]: Zephyr-7b

Uses

If you find a use for it, let me know. In the meantime, I'll try to do better.

Downloads last month: 6

Safetensors

Model size

3B params

Tensor type

F16