Instructions to use metaXu264/Generator_new_tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use metaXu264/Generator_new_tokenizer with Transformers:

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

pipe = pipeline("text-generation", model="metaXu264/Generator_new_tokenizer")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("metaXu264/Generator_new_tokenizer")
model = AutoModelForCausalLM.from_pretrained("metaXu264/Generator_new_tokenizer")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use metaXu264/Generator_new_tokenizer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "metaXu264/Generator_new_tokenizer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "metaXu264/Generator_new_tokenizer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/metaXu264/Generator_new_tokenizer

SGLang

How to use metaXu264/Generator_new_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 "metaXu264/Generator_new_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": "metaXu264/Generator_new_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 "metaXu264/Generator_new_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": "metaXu264/Generator_new_tokenizer",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use metaXu264/Generator_new_tokenizer with Docker Model Runner:
```
docker model run hf.co/metaXu264/Generator_new_tokenizer
```

Generator_new_tokenizer

Commit History

Resize embeddings to match 4260-token tokenizer

192f9c4

XuJP264 commited on Feb 3

Declare CRISPR control tokens as additional_special_tokens

8426321

XuJP264 commited on Feb 3

Update tokenizer source and config vocab_size to 4260

47922fc

XuJP264 commited on Feb 3

Resolve README conflict and merge HF initial commit

6ab833d

XuJP264 commited on Feb 2

Add updated vocab with CRISPR/Cas special tokens

4357886

XuJP264 commited on Feb 2

initial commit

ccd015d
verified

metaXu264 commited on Feb 2

Commit History

Resize embeddings to match 4260-token tokenizer 192f9c4

Declare CRISPR control tokens as additional_special_tokens 8426321

Update tokenizer source and config vocab_size to 4260 47922fc

Resolve README conflict and merge HF initial commit 6ab833d

Add updated vocab with CRISPR/Cas special tokens 4357886

initial commit ccd015d verified

Resize embeddings to match 4260-token tokenizer

192f9c4

Declare CRISPR control tokens as additional_special_tokens

8426321

Update tokenizer source and config vocab_size to 4260

47922fc

Resolve README conflict and merge HF initial commit

6ab833d

Add updated vocab with CRISPR/Cas special tokens

4357886

initial commit

ccd015d
verified