Instructions to use Recor2d/GPT2-ChineseDevBench with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Recor2d/GPT2-ChineseDevBench with Transformers:

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

pipe = pipeline("text-generation", model="Recor2d/GPT2-ChineseDevBench")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Recor2d/GPT2-ChineseDevBench")
model = AutoModelForCausalLM.from_pretrained("Recor2d/GPT2-ChineseDevBench", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Recor2d/GPT2-ChineseDevBench with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Recor2d/GPT2-ChineseDevBench"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Recor2d/GPT2-ChineseDevBench",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Recor2d/GPT2-ChineseDevBench

SGLang

How to use Recor2d/GPT2-ChineseDevBench 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 "Recor2d/GPT2-ChineseDevBench" \
    --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": "Recor2d/GPT2-ChineseDevBench",
		"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 "Recor2d/GPT2-ChineseDevBench" \
        --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": "Recor2d/GPT2-ChineseDevBench",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Recor2d/GPT2-ChineseDevBench with Docker Model Runner:
```
docker model run hf.co/Recor2d/GPT2-ChineseDevBench
```

Recor2d commited on Jun 8

Commit

ef7b750

verified ·

1 Parent(s): 81207a2

Create README.md

Browse files

Files changed (1) hide show

README.md +40 -0

README.md ADDED Viewed

	@@ -0,0 +1,40 @@

+---
+language:
+- zh
+license: apache-2.0
+library_name: transformers
+pipeline_tag: text-generation
+base_model: uer/gpt2-chinese-cluecorpussmall
+tags:
+- gpt2
+- chinese
+- text-generation
+---
+# GPT2-ChineseDevBench
+This model is based on `uer/gpt2-chinese-cluecorpussmall` and is intended for Chinese text generation experiments.
+## Model Details
+- Base model: `uer/gpt2-chinese-cluecorpussmall`
+- Language: Chinese
+- Task: Text Generation
+- Framework: Transformers / PyTorch
+## Intended Use
+This model can be used for Chinese text generation research, testing, and development experiments.
+## How to Use
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
+model_id = "Recor2d/GPT2-ChineseDevBench"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+print(generator("这是很久之前的事情了", max_length=100, do_sample=True))