Instructions to use NeTSlab/gpt2_parfind_nl_zh_equal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NeTSlab/gpt2_parfind_nl_zh_equal with Transformers:

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

pipe = pipeline("text-generation", model="NeTSlab/gpt2_parfind_nl_zh_equal")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NeTSlab/gpt2_parfind_nl_zh_equal")
model = AutoModelForCausalLM.from_pretrained("NeTSlab/gpt2_parfind_nl_zh_equal")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NeTSlab/gpt2_parfind_nl_zh_equal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NeTSlab/gpt2_parfind_nl_zh_equal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NeTSlab/gpt2_parfind_nl_zh_equal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NeTSlab/gpt2_parfind_nl_zh_equal

SGLang

How to use NeTSlab/gpt2_parfind_nl_zh_equal 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 "NeTSlab/gpt2_parfind_nl_zh_equal" \
    --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": "NeTSlab/gpt2_parfind_nl_zh_equal",
		"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 "NeTSlab/gpt2_parfind_nl_zh_equal" \
        --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": "NeTSlab/gpt2_parfind_nl_zh_equal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NeTSlab/gpt2_parfind_nl_zh_equal with Docker Model Runner:
```
docker model run hf.co/NeTSlab/gpt2_parfind_nl_zh_equal
```

gpt2_parfind_nl_zh_equal / tokenizer_config.json

achille-fusco

Add files using upload-large-folder tool

9c4a7c1 verified 3 days ago

Raw

History Blame Contribute Delete

1.64 kB

	{
	"added_tokens_decoder": {
	"0": {
	"content": "<pad>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"1": {
	"content": "<unk>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"2": {
	"content": "<s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	},
	"3": {
	"content": "</s>",
	"lstrip": false,
	"normalized": false,
	"rstrip": false,
	"single_word": false,
	"special": true
	}
	},
	"auto_map": {
	"AutoTokenizer": [
	"tokenizer.EnhancedParadigmTokenizerWrapper",
	null
	]
	},
	"bos_token": "<s>",
	"boundaries_discovery": true,
	"boundary_discovery_mode": "space_free_only",
	"boundary_min_sequence_length": 2,
	"boundary_shorter_first": true,
	"boundary_space_marker": "_",
	"clean_up_tokenization_spaces": false,
	"eos_token": "</s>",
	"extra_special_tokens": {},
	"fallback_mode": "none",
	"model_max_length": 1000000000000000019884624838656,
	"null_suffix_token": "ε",
	"null_suffixes_as_tokens": false,
	"pad_token": "<pad>",
	"paradigm_specific_roots": false,
	"paradigm_specific_suffixes": false,
	"paradigm_token_format": "{token}_p{paradigm_idx}",
	"segment_cache_size": 200000,
	"space_free_bootstrap_languages": [
	"zho"
	],
	"tokenizer_class": "EnhancedParadigmTokenizerWrapper",
	"unk_token": "<unk>",
	"use_word_boundaries": false,
	"word_boundary_token": "▁"
	}