Instructions to use flax-community/gpt-neo-125M-code-clippy-dedup with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use flax-community/gpt-neo-125M-code-clippy-dedup with Transformers:

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

pipe = pipeline("text-generation", model="flax-community/gpt-neo-125M-code-clippy-dedup")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("flax-community/gpt-neo-125M-code-clippy-dedup")
model = AutoModelForCausalLM.from_pretrained("flax-community/gpt-neo-125M-code-clippy-dedup")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use flax-community/gpt-neo-125M-code-clippy-dedup with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "flax-community/gpt-neo-125M-code-clippy-dedup"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "flax-community/gpt-neo-125M-code-clippy-dedup",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/flax-community/gpt-neo-125M-code-clippy-dedup

SGLang

How to use flax-community/gpt-neo-125M-code-clippy-dedup 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 "flax-community/gpt-neo-125M-code-clippy-dedup" \
    --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": "flax-community/gpt-neo-125M-code-clippy-dedup",
		"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 "flax-community/gpt-neo-125M-code-clippy-dedup" \
        --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": "flax-community/gpt-neo-125M-code-clippy-dedup",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use flax-community/gpt-neo-125M-code-clippy-dedup with Docker Model Runner:
```
docker model run hf.co/flax-community/gpt-neo-125M-code-clippy-dedup
```

gpt-neo-125M-code-clippy-dedup

Commit History

Update README.md

b4ba7c8

naruto7 commited on Jul 26, 2021

Update README.md

2090875

ncoop57 commited on Jul 25, 2021

Update README.md

680d68f

ncoop57 commited on Jul 25, 2021

Update README.md

040faaf

ncoop57 commited on Jul 25, 2021

Update README.md

32fe3c4

ncoop57 commited on Jul 25, 2021

Update README.md

4d4c2ea

ncoop57 commited on Jul 23, 2021

Update README.md

71bd15f

ncoop57 commited on Jul 23, 2021

Update README.md

b1b1363

ncoop57 commited on Jul 23, 2021

Create README.md

a7706eb

ncoop57 commited on Jul 23, 2021

Maybe fix tokenizer

9cd4da9

ncoop57 commited on Jul 17, 2021

Add tokenizer and pytorch version of model

0eaa057

ncoop57 commited on Jul 17, 2021

Add most current checkpoint model

8a5cb9d

ncoop57 commited on Jul 17, 2021

initial commit

b4e1b67

system HF Staff commited on Jul 17, 2021

Commit History

Update README.md b4ba7c8

Update README.md 2090875

Update README.md 680d68f

Update README.md 040faaf

Update README.md 32fe3c4

Update README.md 4d4c2ea

Update README.md 71bd15f

Update README.md b1b1363

Create README.md a7706eb

Maybe fix tokenizer 9cd4da9

Add tokenizer and pytorch version of model 0eaa057

Add most current checkpoint model 8a5cb9d

initial commit b4e1b67

Update README.md

b4ba7c8

Update README.md

2090875

Update README.md

680d68f

Update README.md

040faaf

Update README.md

32fe3c4

Update README.md

4d4c2ea

Update README.md

71bd15f

Update README.md

b1b1363

Create README.md

a7706eb

Maybe fix tokenizer

9cd4da9

Add tokenizer and pytorch version of model

0eaa057

Add most current checkpoint model

8a5cb9d

initial commit

b4e1b67