Instructions to use timorobrecht/full_chinese_gpu3.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use timorobrecht/full_chinese_gpu3.1 with Transformers:

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

pipe = pipeline("text-generation", model="timorobrecht/full_chinese_gpu3.1", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("timorobrecht/full_chinese_gpu3.1", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use timorobrecht/full_chinese_gpu3.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "timorobrecht/full_chinese_gpu3.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "timorobrecht/full_chinese_gpu3.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/timorobrecht/full_chinese_gpu3.1

SGLang

How to use timorobrecht/full_chinese_gpu3.1 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 "timorobrecht/full_chinese_gpu3.1" \
    --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": "timorobrecht/full_chinese_gpu3.1",
		"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 "timorobrecht/full_chinese_gpu3.1" \
        --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": "timorobrecht/full_chinese_gpu3.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use timorobrecht/full_chinese_gpu3.1 with Docker Model Runner:
```
docker model run hf.co/timorobrecht/full_chinese_gpu3.1
```

full_chinese_gpu3.1 / tokenizer_config.json

timorobrecht

Add fast tokenizer and benchmark classification compatibility

b187e25 verified 7 days ago

Raw

History Blame Contribute Delete

539 Bytes

	{
	"backend": "tokenizers",
	"bos_token": "<s>",
	"eos_token": "</s>",
	"jieba": true,
	"model_max_length": 512,
	"pad_token": "<pad>",
	"pinyin_format": "pinyin-code",
	"tokenizer_class": "EncodedMandarinTokenizerFast",
	"transliteration": "pinyin-code",
	"unk_token": "<unk>",
	"use_jieba": true,
	"auto_map": {
	"AutoTokenizer": [
	"tokenization_pinyin_code.EncodedMandarinTokenizer",
	"tokenization_pinyin_code.EncodedMandarinTokenizerFast"
	]
	},
	"tokenizer_kind": "sentencepiece"
	}