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

Libraries

How to use marcellopoliti/codeparrot-ds with Transformers:

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

pipe = pipeline("text-generation", model="marcellopoliti/codeparrot-ds")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("marcellopoliti/codeparrot-ds")
model = AutoModelForCausalLM.from_pretrained("marcellopoliti/codeparrot-ds")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use marcellopoliti/codeparrot-ds with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/marcellopoliti/codeparrot-ds

SGLang

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

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

codeparrot-ds

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

Loss: 8.4509

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0005
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 256
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 1000
num_epochs: 1
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
9.0174	0.1606	5	8.9674
8.928	0.3213	10	8.9222
8.8832	0.4819	15	8.8534
8.7662	0.6426	20	8.7513
8.6144	0.8032	25	8.6010
8.49	0.9639	30	8.4509

Framework versions

Transformers 4.48.3
Pytorch 2.5.1+cu124
Datasets 3.3.2
Tokenizers 0.21.0

Downloads last month: 2

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for marcellopoliti/codeparrot-ds

Base model

openai-community/gpt2

Finetuned

(2165)

this model