Instructions to use arvkevi/python-bytes-distilgpt2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arvkevi/python-bytes-distilgpt2 with Transformers:

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

pipe = pipeline("text-generation", model="arvkevi/python-bytes-distilgpt2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arvkevi/python-bytes-distilgpt2")
model = AutoModelForCausalLM.from_pretrained("arvkevi/python-bytes-distilgpt2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use arvkevi/python-bytes-distilgpt2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arvkevi/python-bytes-distilgpt2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arvkevi/python-bytes-distilgpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/arvkevi/python-bytes-distilgpt2

SGLang

How to use arvkevi/python-bytes-distilgpt2 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 "arvkevi/python-bytes-distilgpt2" \
    --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": "arvkevi/python-bytes-distilgpt2",
		"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 "arvkevi/python-bytes-distilgpt2" \
        --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": "arvkevi/python-bytes-distilgpt2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use arvkevi/python-bytes-distilgpt2 with Docker Model Runner:
```
docker model run hf.co/arvkevi/python-bytes-distilgpt2
```

arvkevi commited on Aug 3, 2022

Commit

7f6228b

1 Parent(s): e335bb0

Model save

Browse files

Files changed (2) hide show

pytorch_model.bin +1 -1
runs/Aug03_12-07-59_5f3a3d0f848f/events.out.tfevents.1659528494.5f3a3d0f848f.384.0 +2 -2

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7b4271fa4d74764b371114c5822c7480f6d73a422945d9f72958b97dfa5b40
 size 333969117

 version https://git-lfs.github.com/spec/v1
+oid sha256:fa27a87af23c24c8d3d04c08faf5d4c14921973e5631ac03272ea0d497a789e4
 size 333969117

runs/Aug03_12-07-59_5f3a3d0f848f/events.out.tfevents.1659528494.5f3a3d0f848f.384.0 CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6eb9b483d2591e32969c0a15ef9f271f83d8bb4695b2d9f0c1d6641af303c59
-size 4165

 version https://git-lfs.github.com/spec/v1
+oid sha256:4d1c1d418cc261bfa60172b71eebb342670ee171b75acbf7759cf1d602f10d27
+size 6717