Instructions to use transformers-community/constrained-beam-search with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use transformers-community/constrained-beam-search with Transformers:

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

pipe = pipeline("text-generation", model="transformers-community/constrained-beam-search")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("transformers-community/constrained-beam-search")
model = AutoModelForCausalLM.from_pretrained("transformers-community/constrained-beam-search")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use transformers-community/constrained-beam-search with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "transformers-community/constrained-beam-search"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "transformers-community/constrained-beam-search",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/transformers-community/constrained-beam-search

SGLang

How to use transformers-community/constrained-beam-search 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 "transformers-community/constrained-beam-search" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "transformers-community/constrained-beam-search",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "transformers-community/constrained-beam-search" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "transformers-community/constrained-beam-search",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use transformers-community/constrained-beam-search with Docker Model Runner:
```
docker model run hf.co/transformers-community/constrained-beam-search
```

Fix to avoid error with synced_gpus

by NicolasBFR - opened Nov 5, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-1

NicolasBFR

Nov 5, 2025

Add a default value to the argument synced_gpus to avoid this error:

Traceback (most recent call last):
  File "myFolder/src/translationProject/main.py", line 12, in <module>
    outputs = model.generate(
  File "myFolder/.venv/lib64/python3.9/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
    return func(*args, **kwargs)
  File "myFolder/.venv/lib/python3.9/site-packages/transformers/generation/utils.py", line 2367, in generate
    return custom_generate_function(model=self, **generate_arguments)
  File "/root/.cache/huggingface/modules/transformers_modules/transformers_hyphen_community/constrained_hyphen_beam_hyphen_search/3081418faf290f61bc253e649b0033adf877e655/custom_generate/generate.py", line 338, in generate
    generation_outputs = GenerationMixin.generate(
  File "myFolder/.venv/lib64/python3.9/site-packages/torch/utils/_contextlib.py", line 120, in decorate_context
    return func(*args, **kwargs)
  File "myFolder/.venv/lib/python3.9/site-packages/transformers/generation/utils.py", line 2564, in generate
    result = decoding_method(
TypeError: _constrained_beam_search() missing 1 required positional argument: 'synced_gpus'

Fix to avoid error with synced_gpus86a6a26e

RaushanTurganbay

Transformers Community org Nov 10, 2025

Yep, makes sense! Thanks

RaushanTurganbay changed pull request status to merged Nov 10, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment