Instructions to use shibing624/code-autocomplete-gpt2-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shibing624/code-autocomplete-gpt2-base with Transformers:

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

pipe = pipeline("text-generation", model="shibing624/code-autocomplete-gpt2-base")

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

tokenizer = AutoTokenizer.from_pretrained("shibing624/code-autocomplete-gpt2-base")
model = AutoModelForCausalLM.from_pretrained("shibing624/code-autocomplete-gpt2-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use shibing624/code-autocomplete-gpt2-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shibing624/code-autocomplete-gpt2-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shibing624/code-autocomplete-gpt2-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/shibing624/code-autocomplete-gpt2-base

SGLang

How to use shibing624/code-autocomplete-gpt2-base 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 "shibing624/code-autocomplete-gpt2-base" \
    --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": "shibing624/code-autocomplete-gpt2-base",
		"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 "shibing624/code-autocomplete-gpt2-base" \
        --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": "shibing624/code-autocomplete-gpt2-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use shibing624/code-autocomplete-gpt2-base with Docker Model Runner:
```
docker model run hf.co/shibing624/code-autocomplete-gpt2-base
```

shibing624 commited on Feb 11, 2022

Commit

9a23788

1 Parent(s): 07a5a56

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -13,11 +13,11 @@ license: "apache-2.0"
 # GPT2 for Code AutoComplete Model
 code-autocomplete, a code completion plugin for Python.
-**code-autocomplete**实现了Python代码行粒度和块粒度自动补全功能。
 ## Usage
-本项目开源在中文文本纠错项目：[code-autocomplete](https://github.com/shibing624/code-autocomplete)，可支持GPT2模型，通过如下命令调用：
 ```python
 from autocomplete.gpt2 import Infer
@@ -26,7 +26,7 @@ i = m.predict('import torch.nn as')
 print(i)
 ```
-当然，你也可使用官方的huggingface/transformers调用：
 *Please use 'GPT2' related functions to load this model!*
@@ -111,7 +111,7 @@ Process finished with exit code 0
 ```
-模型文件组成：
 ```
 code-autocomplete-gpt2-base
 ├── config.json
@@ -122,8 +122,8 @@ code-autocomplete-gpt2-base
 └── vocab.json
 ```
-### 训练数据集
-#### pytorch_awesome的所有项目代码
 download [code-autocomplete](https://github.com/shibing624/code-autocomplete),
 ```shell
@@ -131,7 +131,7 @@ cd autocomplete
 python create_dataset.py
 ```
-如果需要训练code-autocomplete，请参考[https://github.com/shibing624/code-autocomplete/blob/main/autocomplete/gpt2.py](https://github.com/shibing624/code-autocomplete/blob/main/autocomplete/gpt2.py)
 ### About GPT2

 # GPT2 for Code AutoComplete Model
 code-autocomplete, a code completion plugin for Python.
+**code-autocomplete** can Automatic completion of code line granularity and block granularity.
 ## Usage
+Open source repo：[code-autocomplete](https://github.com/shibing624/code-autocomplete)，support GPT2 model, usage：
 ```python
 from autocomplete.gpt2 import Infer
 print(i)
 ```
+Also, use huggingface/transformers：
 *Please use 'GPT2' related functions to load this model!*
 ```
+Model files：
 ```
 code-autocomplete-gpt2-base
 ├── config.json
 └── vocab.json
 ```
+### Train data
+#### pytorch_awesome projects source code
 download [code-autocomplete](https://github.com/shibing624/code-autocomplete),
 ```shell
 python create_dataset.py
 ```
+If you want train code-autocomplete GPT2 model，refer [https://github.com/shibing624/code-autocomplete/blob/main/autocomplete/gpt2.py](https://github.com/shibing624/code-autocomplete/blob/main/autocomplete/gpt2.py)
 ### About GPT2