Instructions to use ottema/structfix-codet5p-220m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ottema/structfix-codet5p-220m with Transformers:

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

pipe = pipeline("text-generation", model="ottema/structfix-codet5p-220m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("ottema/structfix-codet5p-220m")
model = AutoModelForSeq2SeqLM.from_pretrained("ottema/structfix-codet5p-220m", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ottema/structfix-codet5p-220m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ottema/structfix-codet5p-220m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ottema/structfix-codet5p-220m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ottema/structfix-codet5p-220m

SGLang

How to use ottema/structfix-codet5p-220m 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 "ottema/structfix-codet5p-220m" \
    --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": "ottema/structfix-codet5p-220m",
		"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 "ottema/structfix-codet5p-220m" \
        --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": "ottema/structfix-codet5p-220m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ottema/structfix-codet5p-220m with Docker Model Runner:
```
docker model run hf.co/ottema/structfix-codet5p-220m
```

luis-otte commited on Jun 10

Commit

497288f

verified ·

1 Parent(s): 29cc076

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -217,7 +217,7 @@ This was discovered through a showcase validation suite (100 inferences per exam
 ## Related
 - [StructFix-Bench](https://huggingface.co/datasets/ottema/structfix-bench) — dataset and benchmark
-- [ConstraintDSL](https://github.com/ottema/constraint-dsl) — DSL specification and compilers
 ## Citation

 ## Related
 - [StructFix-Bench](https://huggingface.co/datasets/ottema/structfix-bench) — dataset and benchmark
+- [ConstraintDSL](https://huggingface.co/datasets/ottema/constraint-dsl) — DSL specification and compilers
 ## Citation