Instructions to use transformersbook/codeparrot-small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use transformersbook/codeparrot-small with Transformers:

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

pipe = pipeline("text-generation", model="transformersbook/codeparrot-small")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("transformersbook/codeparrot-small")
model = AutoModelForCausalLM.from_pretrained("transformersbook/codeparrot-small")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use transformersbook/codeparrot-small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/transformersbook/codeparrot-small

SGLang

How to use transformersbook/codeparrot-small 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 "transformersbook/codeparrot-small" \
    --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": "transformersbook/codeparrot-small",
		"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 "transformersbook/codeparrot-small" \
        --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": "transformersbook/codeparrot-small",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use transformersbook/codeparrot-small with Docker Model Runner:
```
docker model run hf.co/transformersbook/codeparrot-small
```

lvwerra HF Staff commited on Aug 23, 2021

Commit

cd6f029

1 Parent(s): e3d9b66

fix typo

Browse files

Files changed (1) hide show

codeparrot_training.py +3 -3

codeparrot_training.py CHANGED Viewed

@@ -123,11 +123,11 @@ config = {"train_batch_size": 12,
           "lr_scheduler_type": "cosine",
           "num_warmup_steps": 2000,
           "gradient_accumulation_steps": 1,
-          "max_train_steps": 8192,
-          "max_eval_steps": 512,
           "seq_length": 1024,
           "seed": 1,
-          "save_checkpoint_steps":512,}
 args = Namespace(**config)
 set_seed(args.seed)

           "lr_scheduler_type": "cosine",
           "num_warmup_steps": 2000,
           "gradient_accumulation_steps": 1,
+          "max_train_steps": 150_000,
+          "max_eval_steps": -1,
           "seq_length": 1024,
           "seed": 1,
+          "save_checkpoint_steps": 15_000}
 args = Namespace(**config)
 set_seed(args.seed)