Instructions to use claudios/CodeGPT-small-java-adaptedGPT2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use claudios/CodeGPT-small-java-adaptedGPT2 with Transformers:

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

pipe = pipeline("text-generation", model="claudios/CodeGPT-small-java-adaptedGPT2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("claudios/CodeGPT-small-java-adaptedGPT2")
model = AutoModelForCausalLM.from_pretrained("claudios/CodeGPT-small-java-adaptedGPT2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use claudios/CodeGPT-small-java-adaptedGPT2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "claudios/CodeGPT-small-java-adaptedGPT2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "claudios/CodeGPT-small-java-adaptedGPT2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/claudios/CodeGPT-small-java-adaptedGPT2

SGLang

How to use claudios/CodeGPT-small-java-adaptedGPT2 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 "claudios/CodeGPT-small-java-adaptedGPT2" \
    --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": "claudios/CodeGPT-small-java-adaptedGPT2",
		"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 "claudios/CodeGPT-small-java-adaptedGPT2" \
        --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": "claudios/CodeGPT-small-java-adaptedGPT2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use claudios/CodeGPT-small-java-adaptedGPT2 with Docker Model Runner:
```
docker model run hf.co/claudios/CodeGPT-small-java-adaptedGPT2
```

claudios commited on May 22, 2024

Commit

71b8173

verified ·

1 Parent(s): 74b2966

Update tokenizer_config.json

Browse files

Files changed (1) hide show

tokenizer_config.json +1 -1

tokenizer_config.json CHANGED Viewed

@@ -41,7 +41,7 @@
   "eos_token": "</s>",
   "errors": "replace",
   "full_tokenizer_file": null,
-  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|UNKNOWN|>"

   "eos_token": "</s>",
   "errors": "replace",
   "full_tokenizer_file": null,
+  "model_max_length": 1024,
   "pad_token": "<pad>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|UNKNOWN|>"