Instructions to use TerminatorPower/ezellm-lite-tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TerminatorPower/ezellm-lite-tokenizer with Transformers:

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

pipe = pipeline("text-generation", model="TerminatorPower/ezellm-lite-tokenizer")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("TerminatorPower/ezellm-lite-tokenizer", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TerminatorPower/ezellm-lite-tokenizer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/TerminatorPower/ezellm-lite-tokenizer

SGLang

How to use TerminatorPower/ezellm-lite-tokenizer 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 "TerminatorPower/ezellm-lite-tokenizer" \
    --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": "TerminatorPower/ezellm-lite-tokenizer",
		"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 "TerminatorPower/ezellm-lite-tokenizer" \
        --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": "TerminatorPower/ezellm-lite-tokenizer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use TerminatorPower/ezellm-lite-tokenizer with Docker Model Runner:
```
docker model run hf.co/TerminatorPower/ezellm-lite-tokenizer
```

ezellm-lite-tokenizer / tokenizer_config.json

TerminatorPower

Upload ezellm-lite tokenizer (24,600 vocab, FIM + repo specials)

36f1b8c verified 8 days ago

raw

history blame contribute delete

4.6 kB

	{
	"backend": "tokenizers",
	"tokenizer_class": "TokenizersBackend",
	"model_max_length": 1e+30,
	"clean_up_tokenization_spaces": false,
	"bos_token": null,
	"eos_token": "<\|endoftext\|>",
	"unk_token": null,
	"pad_token": "<\|endoftext\|>",
	"added_tokens_decoder": {
	"24576": {
	"content": "<\|endoftext\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24577": {
	"content": "<\|fim_prefix\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24578": {
	"content": "<\|fim_middle\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24579": {
	"content": "<\|fim_suffix\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24580": {
	"content": "<\|fim_pad\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24581": {
	"content": "<\|file_sep\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24582": {
	"content": "<\|repo_name\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24583": {
	"content": "<\|filename\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24584": {
	"content": "<\|reserved_0\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24585": {
	"content": "<\|reserved_1\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24586": {
	"content": "<\|reserved_2\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24587": {
	"content": "<\|reserved_3\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24588": {
	"content": "<\|reserved_4\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24589": {
	"content": "<\|reserved_5\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24590": {
	"content": "<\|reserved_6\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24591": {
	"content": "<\|reserved_7\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24592": {
	"content": "<\|reserved_8\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24593": {
	"content": "<\|reserved_9\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24594": {
	"content": "<\|reserved_10\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24595": {
	"content": "<\|reserved_11\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24596": {
	"content": "<\|reserved_12\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24597": {
	"content": "<\|reserved_13\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24598": {
	"content": "<\|reserved_14\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	},
	"24599": {
	"content": "<\|reserved_15\|>",
	"single_word": false,
	"lstrip": false,
	"rstrip": false,
	"normalized": false,
	"special": true
	}
	}
	}