Instructions to use junnyu/roformer_chinese_sim_char_small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use junnyu/roformer_chinese_sim_char_small with Transformers:

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

pipe = pipeline("text-generation", model="junnyu/roformer_chinese_sim_char_small")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("junnyu/roformer_chinese_sim_char_small")
model = AutoModelForCausalLM.from_pretrained("junnyu/roformer_chinese_sim_char_small", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use junnyu/roformer_chinese_sim_char_small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/junnyu/roformer_chinese_sim_char_small

SGLang

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

Docker Model Runner
How to use junnyu/roformer_chinese_sim_char_small with Docker Model Runner:
```
docker model run hf.co/junnyu/roformer_chinese_sim_char_small
```

junnyu commited on Jul 9, 2021

Commit

2ac2f21

1 Parent(s): cbd75d6

Create README.md

Browse files

Files changed (1) hide show

README.md +15 -0

README.md ADDED Viewed

	@@ -0,0 +1,15 @@

+---
+language: zh
+tags:
+- roformer
+- pytorch
+- tf2.0
+widget:
+- text: "今天[MASK]很好，我想去公园玩！"
+---
+## 介绍
+### tf版本
+https://github.com/ZhuiyiTechnology/roformer
+### pytorch版本+tf2.0版本
+https://github.com/JunnYu/RoFormer_pytorch