Instructions to use Kai12341/codeparrot-ds-fast with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kai12341/codeparrot-ds-fast with Transformers:

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

pipe = pipeline("text-generation", model="Kai12341/codeparrot-ds-fast")

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

tokenizer = AutoTokenizer.from_pretrained("Kai12341/codeparrot-ds-fast")
model = AutoModelForCausalLM.from_pretrained("Kai12341/codeparrot-ds-fast", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kai12341/codeparrot-ds-fast with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kai12341/codeparrot-ds-fast"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kai12341/codeparrot-ds-fast",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kai12341/codeparrot-ds-fast

SGLang

How to use Kai12341/codeparrot-ds-fast 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 "Kai12341/codeparrot-ds-fast" \
    --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": "Kai12341/codeparrot-ds-fast",
		"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 "Kai12341/codeparrot-ds-fast" \
        --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": "Kai12341/codeparrot-ds-fast",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kai12341/codeparrot-ds-fast with Docker Model Runner:
```
docker model run hf.co/Kai12341/codeparrot-ds-fast
```

codeparrot-ds-fast

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

Loss: 3.7034

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: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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: 100
num_epochs: 1
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
5.0073	0.0533	200	5.1243
4.685	0.1067	400	4.8637
4.5059	0.16	600	4.6787
4.3095	0.2133	800	4.5581
4.1536	0.2667	1000	4.4384
4.0469	0.32	1200	4.3332
3.9417	0.3733	1400	4.2495
3.841	0.4267	1600	4.1737
3.72	0.48	1800	4.0918
3.6337	0.5333	2000	4.0258
3.5766	0.5867	2200	3.9505
3.5221	0.64	2400	3.8845
3.4027	0.6933	2600	3.8252
3.4128	0.7467	2800	3.7814
3.3485	0.8	3000	3.7483
3.3857	0.8533	3200	3.7230
3.2951	0.9067	3400	3.7100
3.3037	0.96	3600	3.7034

Framework versions

Transformers 4.51.1
Pytorch 2.5.1+cu124
Datasets 3.5.0
Tokenizers 0.21.0

Downloads last month: 21

Safetensors

Model size

0.1B params

Tensor type

F32

Model tree for Kai12341/codeparrot-ds-fast

Base model

openai-community/gpt2

Finetuned

(2294)

this model