Instructions to use APMIC/DistilGPT-2-TPU-Fine-tune with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use APMIC/DistilGPT-2-TPU-Fine-tune with Transformers:

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

pipe = pipeline("text-generation", model="APMIC/DistilGPT-2-TPU-Fine-tune")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("APMIC/DistilGPT-2-TPU-Fine-tune")
model = AutoModelForCausalLM.from_pretrained("APMIC/DistilGPT-2-TPU-Fine-tune")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use APMIC/DistilGPT-2-TPU-Fine-tune with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "APMIC/DistilGPT-2-TPU-Fine-tune"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "APMIC/DistilGPT-2-TPU-Fine-tune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/APMIC/DistilGPT-2-TPU-Fine-tune

SGLang

How to use APMIC/DistilGPT-2-TPU-Fine-tune 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 "APMIC/DistilGPT-2-TPU-Fine-tune" \
    --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": "APMIC/DistilGPT-2-TPU-Fine-tune",
		"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 "APMIC/DistilGPT-2-TPU-Fine-tune" \
        --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": "APMIC/DistilGPT-2-TPU-Fine-tune",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use APMIC/DistilGPT-2-TPU-Fine-tune with Docker Model Runner:
```
docker model run hf.co/APMIC/DistilGPT-2-TPU-Fine-tune
```

DistilGPT-2-TPU-Fine-tune / flax_model.msgpack

corrine1106

Upload folder using huggingface_hub

3f8464e about 3 years ago

download

history blame contribute delete

328 MB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 0ee808b2c73bd4903c6b2e69022a4e6bbfb55403c09941a4032163606b15508c
Size of remote file:: 328 MB
SHA256:: 6ef3632b884801b1b1984b7d1e0644c31d4455ee1ba5069e21a611de6e2163d9

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.