Instructions to use MUmairAB/python-code-generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MUmairAB/python-code-generator with Transformers:

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

pipe = pipeline("text-generation", model="MUmairAB/python-code-generator")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MUmairAB/python-code-generator")
model = AutoModelForCausalLM.from_pretrained("MUmairAB/python-code-generator")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MUmairAB/python-code-generator with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MUmairAB/python-code-generator

SGLang

How to use MUmairAB/python-code-generator 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 "MUmairAB/python-code-generator" \
    --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": "MUmairAB/python-code-generator",
		"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 "MUmairAB/python-code-generator" \
        --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": "MUmairAB/python-code-generator",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MUmairAB/python-code-generator with Docker Model Runner:
```
docker model run hf.co/MUmairAB/python-code-generator
```

MUmairAB commited on Jul 27, 2023

Commit

ba24580

1 Parent(s): d23cf16

Training in progress epoch 3

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 2.4439
 - Validation Loss: 2.6055
-- Epoch: 2
 ## Model description
@@ -45,6 +45,7 @@ The following hyperparameters were used during training:
 | 2.4439     | 2.6055          | 0     |
 | 2.4438     | 2.6055          | 1     |
 | 2.4439     | 2.6055          | 2     |
 ### Framework versions

 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Train Loss: 2.4437
 - Validation Loss: 2.6055
+- Epoch: 3
 ## Model description
 | 2.4439     | 2.6055          | 0     |
 | 2.4438     | 2.6055          | 1     |
 | 2.4439     | 2.6055          | 2     |
+| 2.4437     | 2.6055          | 3     |
 ### Framework versions