Instructions to use sharoz/codeparrot-small-custom-functions-dataset-python with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sharoz/codeparrot-small-custom-functions-dataset-python with Transformers:

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

pipe = pipeline("text-generation", model="sharoz/codeparrot-small-custom-functions-dataset-python")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sharoz/codeparrot-small-custom-functions-dataset-python")
model = AutoModelForCausalLM.from_pretrained("sharoz/codeparrot-small-custom-functions-dataset-python", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sharoz/codeparrot-small-custom-functions-dataset-python with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/sharoz/codeparrot-small-custom-functions-dataset-python

SGLang

How to use sharoz/codeparrot-small-custom-functions-dataset-python 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 "sharoz/codeparrot-small-custom-functions-dataset-python" \
    --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": "sharoz/codeparrot-small-custom-functions-dataset-python",
		"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 "sharoz/codeparrot-small-custom-functions-dataset-python" \
        --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": "sharoz/codeparrot-small-custom-functions-dataset-python",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sharoz/codeparrot-small-custom-functions-dataset-python with Docker Model Runner:
```
docker model run hf.co/sharoz/codeparrot-small-custom-functions-dataset-python
```

codeparrot-small-custom-functions-dataset-python / README.md

sharoz

update model card README.md

bcb84c5 about 3 years ago

preview code

Raw

History Blame Contribute Delete

5.36 kB

	---
	license: apache-2.0
	tags:
	- generated_from_trainer
	model-index:
	- name: codeparrot-small-custom-functions-dataset-python
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# codeparrot-small-custom-functions-dataset-python

	This model is a fine-tuned version of [codeparrot/codeparrot-small](https://huggingface.co/codeparrot/codeparrot-small) on the None dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.4238

	## 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: 2e-05
	- train_batch_size: 8
	- eval_batch_size: 8
	- seed: 42
	- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
	- lr_scheduler_type: linear
	- num_epochs: 10

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:-----:\|:----:\|:---------------:\|
	\| 1.216 \| 0.12 \| 1 \| 1.0747 \|
	\| 1.051 \| 0.25 \| 2 \| 1.0005 \|
	\| 0.9855 \| 0.38 \| 3 \| 0.9462 \|
	\| 0.9259 \| 0.5 \| 4 \| 0.9042 \|
	\| 0.9236 \| 0.62 \| 5 \| 0.8675 \|
	\| 0.8644 \| 0.75 \| 6 \| 0.8331 \|
	\| 0.8148 \| 0.88 \| 7 \| 0.8030 \|
	\| 0.7554 \| 1.0 \| 8 \| 0.7800 \|
	\| 0.7815 \| 1.12 \| 9 \| 0.7600 \|
	\| 0.784 \| 1.25 \| 10 \| 0.7440 \|
	\| 0.635 \| 1.38 \| 11 \| 0.7309 \|
	\| 0.6666 \| 1.5 \| 12 \| 0.7170 \|
	\| 0.7676 \| 1.62 \| 13 \| 0.6993 \|
	\| 0.6608 \| 1.75 \| 14 \| 0.6835 \|
	\| 0.6885 \| 1.88 \| 15 \| 0.6696 \|
	\| 0.69 \| 2.0 \| 16 \| 0.6582 \|
	\| 0.6343 \| 2.12 \| 17 \| 0.6463 \|
	\| 0.709 \| 2.25 \| 18 \| 0.6324 \|
	\| 0.5446 \| 2.38 \| 19 \| 0.6206 \|
	\| 0.5298 \| 2.5 \| 20 \| 0.6102 \|
	\| 0.6478 \| 2.62 \| 21 \| 0.6016 \|
	\| 0.546 \| 2.75 \| 22 \| 0.5941 \|
	\| 0.6297 \| 2.88 \| 23 \| 0.5871 \|
	\| 0.4518 \| 3.0 \| 24 \| 0.5814 \|
	\| 0.566 \| 3.12 \| 25 \| 0.5769 \|
	\| 0.6285 \| 3.25 \| 26 \| 0.5702 \|
	\| 0.5938 \| 3.38 \| 27 \| 0.5631 \|
	\| 0.514 \| 3.5 \| 28 \| 0.5568 \|
	\| 0.5113 \| 3.62 \| 29 \| 0.5504 \|
	\| 0.512 \| 3.75 \| 30 \| 0.5451 \|
	\| 0.4392 \| 3.88 \| 31 \| 0.5407 \|
	\| 0.5097 \| 4.0 \| 32 \| 0.5370 \|
	\| 0.4866 \| 4.12 \| 33 \| 0.5326 \|
	\| 0.5028 \| 4.25 \| 34 \| 0.5285 \|
	\| 0.5438 \| 4.38 \| 35 \| 0.5228 \|
	\| 0.5424 \| 4.5 \| 36 \| 0.5166 \|
	\| 0.5156 \| 4.62 \| 37 \| 0.5108 \|
	\| 0.4335 \| 4.75 \| 38 \| 0.5056 \|
	\| 0.4298 \| 4.88 \| 39 \| 0.5013 \|
	\| 0.5268 \| 5.0 \| 40 \| 0.4978 \|
	\| 0.4714 \| 5.12 \| 41 \| 0.4938 \|
	\| 0.4659 \| 5.25 \| 42 \| 0.4907 \|
	\| 0.4573 \| 5.38 \| 43 \| 0.4874 \|
	\| 0.4689 \| 5.5 \| 44 \| 0.4847 \|
	\| 0.4346 \| 5.62 \| 45 \| 0.4824 \|
	\| 0.4563 \| 5.75 \| 46 \| 0.4794 \|
	\| 0.4505 \| 5.88 \| 47 \| 0.4761 \|
	\| 0.7359 \| 6.0 \| 48 \| 0.4732 \|
	\| 0.4704 \| 6.12 \| 49 \| 0.4706 \|
	\| 0.4223 \| 6.25 \| 50 \| 0.4685 \|
	\| 0.4789 \| 6.38 \| 51 \| 0.4651 \|
	\| 0.4402 \| 6.5 \| 52 \| 0.4624 \|
	\| 0.4454 \| 6.62 \| 53 \| 0.4597 \|
	\| 0.4496 \| 6.75 \| 54 \| 0.4566 \|
	\| 0.3942 \| 6.88 \| 55 \| 0.4539 \|
	\| 0.2915 \| 7.0 \| 56 \| 0.4515 \|
	\| 0.3926 \| 7.12 \| 57 \| 0.4496 \|
	\| 0.4102 \| 7.25 \| 58 \| 0.4474 \|
	\| 0.4235 \| 7.38 \| 59 \| 0.4456 \|
	\| 0.4841 \| 7.5 \| 60 \| 0.4441 \|
	\| 0.3914 \| 7.62 \| 61 \| 0.4423 \|
	\| 0.4417 \| 7.75 \| 62 \| 0.4404 \|
	\| 0.4212 \| 7.88 \| 63 \| 0.4384 \|
	\| 0.4343 \| 8.0 \| 64 \| 0.4369 \|
	\| 0.4159 \| 8.12 \| 65 \| 0.4355 \|
	\| 0.4193 \| 8.25 \| 66 \| 0.4343 \|
	\| 0.4393 \| 8.38 \| 67 \| 0.4333 \|
	\| 0.4507 \| 8.5 \| 68 \| 0.4319 \|
	\| 0.3855 \| 8.62 \| 69 \| 0.4305 \|
	\| 0.4064 \| 8.75 \| 70 \| 0.4293 \|
	\| 0.4044 \| 8.88 \| 71 \| 0.4283 \|
	\| 0.2957 \| 9.0 \| 72 \| 0.4275 \|
	\| 0.4442 \| 9.12 \| 73 \| 0.4266 \|
	\| 0.4142 \| 9.25 \| 74 \| 0.4260 \|
	\| 0.4022 \| 9.38 \| 75 \| 0.4253 \|
	\| 0.4161 \| 9.5 \| 76 \| 0.4248 \|
	\| 0.3828 \| 9.62 \| 77 \| 0.4244 \|
	\| 0.384 \| 9.75 \| 78 \| 0.4241 \|
	\| 0.3985 \| 9.88 \| 79 \| 0.4239 \|
	\| 0.4912 \| 10.0 \| 80 \| 0.4238 \|


	### Framework versions

	- Transformers 4.28.1
	- Pytorch 2.0.0+cu118
	- Datasets 2.12.0
	- Tokenizers 0.13.3

	---
	license: apache-2.0
	tags:
	- generated_from_trainer
	model-index:
	- name: codeparrot-small-custom-functions-dataset-python
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	# codeparrot-small-custom-functions-dataset-python

	This model is a fine-tuned version of [codeparrot/codeparrot-small](https://huggingface.co/codeparrot/codeparrot-small) on the None dataset.
	It achieves the following results on the evaluation set:
	- Loss: 0.4238

	## 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: 2e-05
	- train_batch_size: 8
	- eval_batch_size: 8
	- seed: 42
	- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
	- lr_scheduler_type: linear
	- num_epochs: 10

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:-----:\|:----:\|:---------------:\|
	\| 1.216 \| 0.12 \| 1 \| 1.0747 \|
	\| 1.051 \| 0.25 \| 2 \| 1.0005 \|
	\| 0.9855 \| 0.38 \| 3 \| 0.9462 \|
	\| 0.9259 \| 0.5 \| 4 \| 0.9042 \|
	\| 0.9236 \| 0.62 \| 5 \| 0.8675 \|
	\| 0.8644 \| 0.75 \| 6 \| 0.8331 \|
	\| 0.8148 \| 0.88 \| 7 \| 0.8030 \|
	\| 0.7554 \| 1.0 \| 8 \| 0.7800 \|
	\| 0.7815 \| 1.12 \| 9 \| 0.7600 \|
	\| 0.784 \| 1.25 \| 10 \| 0.7440 \|
	\| 0.635 \| 1.38 \| 11 \| 0.7309 \|
	\| 0.6666 \| 1.5 \| 12 \| 0.7170 \|
	\| 0.7676 \| 1.62 \| 13 \| 0.6993 \|
	\| 0.6608 \| 1.75 \| 14 \| 0.6835 \|
	\| 0.6885 \| 1.88 \| 15 \| 0.6696 \|
	\| 0.69 \| 2.0 \| 16 \| 0.6582 \|
	\| 0.6343 \| 2.12 \| 17 \| 0.6463 \|
	\| 0.709 \| 2.25 \| 18 \| 0.6324 \|
	\| 0.5446 \| 2.38 \| 19 \| 0.6206 \|
	\| 0.5298 \| 2.5 \| 20 \| 0.6102 \|
	\| 0.6478 \| 2.62 \| 21 \| 0.6016 \|
	\| 0.546 \| 2.75 \| 22 \| 0.5941 \|
	\| 0.6297 \| 2.88 \| 23 \| 0.5871 \|
	\| 0.4518 \| 3.0 \| 24 \| 0.5814 \|
	\| 0.566 \| 3.12 \| 25 \| 0.5769 \|
	\| 0.6285 \| 3.25 \| 26 \| 0.5702 \|
	\| 0.5938 \| 3.38 \| 27 \| 0.5631 \|
	\| 0.514 \| 3.5 \| 28 \| 0.5568 \|
	\| 0.5113 \| 3.62 \| 29 \| 0.5504 \|
	\| 0.512 \| 3.75 \| 30 \| 0.5451 \|
	\| 0.4392 \| 3.88 \| 31 \| 0.5407 \|
	\| 0.5097 \| 4.0 \| 32 \| 0.5370 \|
	\| 0.4866 \| 4.12 \| 33 \| 0.5326 \|
	\| 0.5028 \| 4.25 \| 34 \| 0.5285 \|
	\| 0.5438 \| 4.38 \| 35 \| 0.5228 \|
	\| 0.5424 \| 4.5 \| 36 \| 0.5166 \|
	\| 0.5156 \| 4.62 \| 37 \| 0.5108 \|
	\| 0.4335 \| 4.75 \| 38 \| 0.5056 \|
	\| 0.4298 \| 4.88 \| 39 \| 0.5013 \|
	\| 0.5268 \| 5.0 \| 40 \| 0.4978 \|
	\| 0.4714 \| 5.12 \| 41 \| 0.4938 \|
	\| 0.4659 \| 5.25 \| 42 \| 0.4907 \|
	\| 0.4573 \| 5.38 \| 43 \| 0.4874 \|
	\| 0.4689 \| 5.5 \| 44 \| 0.4847 \|
	\| 0.4346 \| 5.62 \| 45 \| 0.4824 \|
	\| 0.4563 \| 5.75 \| 46 \| 0.4794 \|
	\| 0.4505 \| 5.88 \| 47 \| 0.4761 \|
	\| 0.7359 \| 6.0 \| 48 \| 0.4732 \|
	\| 0.4704 \| 6.12 \| 49 \| 0.4706 \|
	\| 0.4223 \| 6.25 \| 50 \| 0.4685 \|
	\| 0.4789 \| 6.38 \| 51 \| 0.4651 \|
	\| 0.4402 \| 6.5 \| 52 \| 0.4624 \|
	\| 0.4454 \| 6.62 \| 53 \| 0.4597 \|
	\| 0.4496 \| 6.75 \| 54 \| 0.4566 \|
	\| 0.3942 \| 6.88 \| 55 \| 0.4539 \|
	\| 0.2915 \| 7.0 \| 56 \| 0.4515 \|
	\| 0.3926 \| 7.12 \| 57 \| 0.4496 \|
	\| 0.4102 \| 7.25 \| 58 \| 0.4474 \|
	\| 0.4235 \| 7.38 \| 59 \| 0.4456 \|
	\| 0.4841 \| 7.5 \| 60 \| 0.4441 \|
	\| 0.3914 \| 7.62 \| 61 \| 0.4423 \|
	\| 0.4417 \| 7.75 \| 62 \| 0.4404 \|
	\| 0.4212 \| 7.88 \| 63 \| 0.4384 \|
	\| 0.4343 \| 8.0 \| 64 \| 0.4369 \|
	\| 0.4159 \| 8.12 \| 65 \| 0.4355 \|
	\| 0.4193 \| 8.25 \| 66 \| 0.4343 \|
	\| 0.4393 \| 8.38 \| 67 \| 0.4333 \|
	\| 0.4507 \| 8.5 \| 68 \| 0.4319 \|
	\| 0.3855 \| 8.62 \| 69 \| 0.4305 \|
	\| 0.4064 \| 8.75 \| 70 \| 0.4293 \|
	\| 0.4044 \| 8.88 \| 71 \| 0.4283 \|
	\| 0.2957 \| 9.0 \| 72 \| 0.4275 \|
	\| 0.4442 \| 9.12 \| 73 \| 0.4266 \|
	\| 0.4142 \| 9.25 \| 74 \| 0.4260 \|
	\| 0.4022 \| 9.38 \| 75 \| 0.4253 \|
	\| 0.4161 \| 9.5 \| 76 \| 0.4248 \|
	\| 0.3828 \| 9.62 \| 77 \| 0.4244 \|
	\| 0.384 \| 9.75 \| 78 \| 0.4241 \|
	\| 0.3985 \| 9.88 \| 79 \| 0.4239 \|
	\| 0.4912 \| 10.0 \| 80 \| 0.4238 \|


	### Framework versions

	- Transformers 4.28.1
	- Pytorch 2.0.0+cu118
	- Datasets 2.12.0
	- Tokenizers 0.13.3