Instructions to use einobe13/codeparrot-ds with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use einobe13/codeparrot-ds with Transformers:

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

pipe = pipeline("text-generation", model="einobe13/codeparrot-ds")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("einobe13/codeparrot-ds")
model = AutoModelForCausalLM.from_pretrained("einobe13/codeparrot-ds", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use einobe13/codeparrot-ds with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "einobe13/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": "einobe13/codeparrot-ds",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/einobe13/codeparrot-ds

SGLang

How to use einobe13/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 "einobe13/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": "einobe13/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 "einobe13/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": "einobe13/codeparrot-ds",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use einobe13/codeparrot-ds with Docker Model Runner:
```
docker model run hf.co/einobe13/codeparrot-ds
```

codeparrot-ds

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 7.6296

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: 2
total_train_batch_size: 64
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
training_steps: 1500

Training results

Training Loss	Epoch	Step	Validation Loss
6.4003	0.0019	500	6.5106
7.1264	0.0038	1000	7.2123
7.7135	0.0057	1500	7.6296

Framework versions

Transformers 5.20.2
Pytorch 2.6.0+cu124
Datasets 5.1.0
Tokenizers 0.23.3

Downloads last month: 356

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for einobe13/codeparrot-ds

Base model

openai-community/gpt2

Finetuned

(2302)

this model