Instructions to use LLM-course/simple_tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LLM-course/simple_tokenizer with Transformers:

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

pipe = pipeline("text-generation", model="LLM-course/simple_tokenizer", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("LLM-course/simple_tokenizer", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LLM-course/simple_tokenizer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LLM-course/simple_tokenizer

SGLang

How to use LLM-course/simple_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 "LLM-course/simple_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": "LLM-course/simple_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 "LLM-course/simple_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": "LLM-course/simple_tokenizer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LLM-course/simple_tokenizer with Docker Model Runner:
```
docker model run hf.co/LLM-course/simple_tokenizer
```

simple_tokenizer / vocab.json

pultch

Chess Challenge submission by pultch

ecacb41 verified 4 months ago

raw

history blame contribute delete

886 Bytes

	{
	"[PAD]": 0,
	"[BOS]": 1,
	"[EOS]": 2,
	"[UNK]": 3,
	"K": 4,
	"Q": 5,
	"R": 6,
	"B": 7,
	"N": 8,
	"P": 9,
	"a1": 10,
	"a2": 11,
	"a3": 12,
	"a4": 13,
	"a5": 14,
	"a6": 15,
	"a7": 16,
	"a8": 17,
	"b1": 18,
	"b2": 19,
	"b3": 20,
	"b4": 21,
	"b5": 22,
	"b6": 23,
	"b7": 24,
	"b8": 25,
	"c1": 26,
	"c2": 27,
	"c3": 28,
	"c4": 29,
	"c5": 30,
	"c6": 31,
	"c7": 32,
	"c8": 33,
	"d1": 34,
	"d2": 35,
	"d3": 36,
	"d4": 37,
	"d5": 38,
	"d6": 39,
	"d7": 40,
	"d8": 41,
	"e1": 42,
	"e2": 43,
	"e3": 44,
	"e4": 45,
	"e5": 46,
	"e6": 47,
	"e7": 48,
	"e8": 49,
	"f1": 50,
	"f2": 51,
	"f3": 52,
	"f4": 53,
	"f5": 54,
	"f6": 55,
	"f7": 56,
	"f8": 57,
	"g1": 58,
	"g2": 59,
	"g3": 60,
	"g4": 61,
	"g5": 62,
	"g6": 63,
	"g7": 64,
	"g8": 65,
	"h1": 66,
	"h2": 67,
	"h3": 68,
	"h4": 69,
	"h5": 70,
	"h6": 71,
	"h7": 72,
	"h8": 73
	}