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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sharoz/codebert-python-custom-functions-dataset-python")
model = AutoModelForCausalLM.from_pretrained("sharoz/codebert-python-custom-functions-dataset-python")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

sharoz commited on May 6, 2023

Commit

2012863

1 Parent(s): acc18ad

update model card README.md

Browse files

Files changed (1) hide show

README.md +12 -7

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [neulab/codebert-python](https://huggingface.co/neulab/codebert-python) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1649
 ## Model description
@@ -38,17 +38,22 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 42   | 1.5320          |
-| No log        | 2.0   | 84   | 0.5192          |
-| No log        | 3.0   | 126  | 0.2679          |
-| No log        | 4.0   | 168  | 0.1871          |
-| No log        | 5.0   | 210  | 0.1649          |
 ### Framework versions

 This model is a fine-tuned version of [neulab/codebert-python](https://huggingface.co/neulab/codebert-python) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0151
 ## Model description
 - 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 |
 |:-------------:|:-----:|:----:|:---------------:|
+| 1.9043        | 1.0   | 43   | 1.5089          |
+| 0.5831        | 2.0   | 86   | 0.4039          |
+| 0.3148        | 3.0   | 129  | 0.1510          |
+| 0.2251        | 4.0   | 172  | 0.0710          |
+| 0.0766        | 5.0   | 215  | 0.0442          |
+| 0.0884        | 6.0   | 258  | 0.0287          |
+| 0.0975        | 7.0   | 301  | 0.0210          |
+| 0.1113        | 8.0   | 344  | 0.0183          |
+| 0.0448        | 9.0   | 387  | 0.0162          |
+| 0.029         | 10.0  | 430  | 0.0151          |
 ### Framework versions