Instructions to use Continuous-Rivals-Discrete/langflow-lm1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Continuous-Rivals-Discrete/langflow-lm1b with Transformers:

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

pipe = pipeline("text-generation", model="Continuous-Rivals-Discrete/langflow-lm1b", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForMaskedLM
model = AutoModelForMaskedLM.from_pretrained("Continuous-Rivals-Discrete/langflow-lm1b", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Continuous-Rivals-Discrete/langflow-lm1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Continuous-Rivals-Discrete/langflow-lm1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Continuous-Rivals-Discrete/langflow-lm1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Continuous-Rivals-Discrete/langflow-lm1b

SGLang

How to use Continuous-Rivals-Discrete/langflow-lm1b 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 "Continuous-Rivals-Discrete/langflow-lm1b" \
    --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": "Continuous-Rivals-Discrete/langflow-lm1b",
		"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 "Continuous-Rivals-Discrete/langflow-lm1b" \
        --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": "Continuous-Rivals-Discrete/langflow-lm1b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Continuous-Rivals-Discrete/langflow-lm1b with Docker Model Runner:
```
docker model run hf.co/Continuous-Rivals-Discrete/langflow-lm1b
```

langflow-lm1b / README.md

nealchen

Upload ./README.md with huggingface_hub

d5d395d verified 3 days ago

preview code

raw

history blame contribute delete

1.8 kB

	---
	datasets:
	- dvruette/lm1b
	papers:
	- arxiv: 2604.11748
	language:
	- en
	library_name: transformers
	license: apache-2.0
	metrics:
	- perplexity
	pipeline_tag: text-generation
	---

	# LangFlow

	LangFlow is a continuous diffusion language model that operates in embedding space. Unlike discrete diffusion models (MDLM, SEDD, DUO), LangFlow performs diffusion directly on continuous token embeddings, enabling smoother denoising dynamics.

	For more details, please see our paper: [LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling](https://arxiv.org/abs/2604.11748).


	## Using LangFlow

	To use the pre-trained model for text generation, use the following snippet:

	```python
	from transformers import AutoModelForMaskedLM, AutoTokenizer

	tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')
	model = AutoModelForMaskedLM.from_pretrained('Continuous-Rivals-Discrete/langflow-lm1b', trust_remote_code=True)

	# Generate samples
	samples = model.generate_samples(num_samples=5, num_steps=128)
	texts = tokenizer.batch_decode(samples, skip_special_tokens=True)
	for text in texts:
	print(text)
	```

	## Model Details

	- Architecture: DiT (Diffusion Transformer) backbone with adaptive layer normalization
	- Context Length: 128 tokens
	- Parameters: ~130M parameters (similar to GPT-2 small)
	- Training: 1M steps on LM1B corpus
	- Tokenizer: bert-base-uncased tokenizer (30,522 vocab size)

	## Citation

	```
	@article{chen2026langflow,
	title={LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling},
	author={Chen, Yuxin and Liang, Chumeng and Sui, Hangke and Guo, Ruihan and Cheng, Chaoran and You, Jiaxuan and Liu, Ge},
	journal={arXiv preprint arXiv:2604.11748},
	year={2026}
	}
	```

	## Model Card Contact

	Chumeng Liang (chumengl@illinois.edu)