Instructions to use Felladrin/Sheared-Pythia-160m-Platypus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Felladrin/Sheared-Pythia-160m-Platypus with Transformers:

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

pipe = pipeline("text-generation", model="Felladrin/Sheared-Pythia-160m-Platypus")

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

tokenizer = AutoTokenizer.from_pretrained("Felladrin/Sheared-Pythia-160m-Platypus")
model = AutoModelForCausalLM.from_pretrained("Felladrin/Sheared-Pythia-160m-Platypus", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Felladrin/Sheared-Pythia-160m-Platypus with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Felladrin/Sheared-Pythia-160m-Platypus"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Felladrin/Sheared-Pythia-160m-Platypus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Felladrin/Sheared-Pythia-160m-Platypus

SGLang

How to use Felladrin/Sheared-Pythia-160m-Platypus 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 "Felladrin/Sheared-Pythia-160m-Platypus" \
    --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": "Felladrin/Sheared-Pythia-160m-Platypus",
		"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 "Felladrin/Sheared-Pythia-160m-Platypus" \
        --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": "Felladrin/Sheared-Pythia-160m-Platypus",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Felladrin/Sheared-Pythia-160m-Platypus with Docker Model Runner:
```
docker model run hf.co/Felladrin/Sheared-Pythia-160m-Platypus
```

Sheared-Pythia-160m-Platypus / README.md

Felladrin

Add link to GGUF version

4fb3048 verified over 2 years ago

preview code

Raw History Blame Contribute Delete

1.57 kB

metadata

license: cc-by-nc-sa-4.0
base_model: princeton-nlp/Sheared-Pythia-160m
datasets:
  - garage-bAInd/Open-Platypus
widget:
  - text: |-
      ### User:
      What are some popular locations for visiting around the world?
      ### Assistant:
  - text: >-
      ### User:

      How do meteorologists predict how much air pollution will be produced in
      the next year?

      ### Assistant:
  - text: |-
      ### User:
      How to become more healthy?
      ### Assistant:
  - text: |-
      ### User:
      Write the specs of a game about dragons and warriors in a fantasy world.
      ### Assistant:
inference:
  parameters:
    max_new_tokens: 64
    repetition_penalty: 1.18

Princeton NLP's Sheared-Pythia-160m trained on the Open-Platypus dataset

Base model: princeton-nlp/Sheared-Pythia-160m
Dataset: garage-bAInd/Open-Platypus
Trained with AutoTrain Advanced using these parameters
Availability in other ML formats:
- GGUF: Felladrin/gguf-Sheared-Pythia-160m-Platypus
- ONNX: Felladrin/onnx-Sheared-Pythia-160m-Platypus

Recommended Prompt Format

### User:
<message>
### Assistant: