Instructions to use fredzzp/open-dcoder-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fredzzp/open-dcoder-0.5B with Transformers:

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

pipe = pipeline("text-generation", model="fredzzp/open-dcoder-0.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fredzzp/open-dcoder-0.5B")
model = AutoModelForCausalLM.from_pretrained("fredzzp/open-dcoder-0.5B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use fredzzp/open-dcoder-0.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fredzzp/open-dcoder-0.5B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fredzzp/open-dcoder-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fredzzp/open-dcoder-0.5B

SGLang

How to use fredzzp/open-dcoder-0.5B 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 "fredzzp/open-dcoder-0.5B" \
    --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": "fredzzp/open-dcoder-0.5B",
		"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 "fredzzp/open-dcoder-0.5B" \
        --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": "fredzzp/open-dcoder-0.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fredzzp/open-dcoder-0.5B with Docker Model Runner:
```
docker model run hf.co/fredzzp/open-dcoder-0.5B
```

open-dcoder-0.5B / README.md

nielsr HF Staff

Add paper link and improve model card metadata

c678e54 verified 14 days ago

2.65 kB

language:
  - code
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
tags:
  - masked-diffusion
  - code-generation
  - qwen2

Open Diffusion Large Language Models for Code Generation

This repository contains the weights and custom code for the fredzzp/open-dcoder-0.5B model, a masked diffusion model for code generation based on the Qwen2 architecture.

The model was introduced in the paper Don't Retrain, Align: Adapting Autoregressive LMs to Diffusion LMs via Representation Alignment.

Code: pengzhangzhi/Open-dLLM
Blog: Notion Blog

This model uses bidirectional attention and must be used with the custom diffusion_generate method.

How to Use

First, make sure you have the latest transformers library installed.

pip install transformers torch huggingface_hub

You can then use the model for generation. Note: You must pass trust_remote_code=True to load the custom model architecture.

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "fredzzp/open-dcoder-0.5B"
device = "cuda" if torch.cuda.is_available() else "cpu"

# trust_remote_code=True is essential
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    trust_remote_code=True
).to(device)

prompt = "def fibonacci(n):"
input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)

# The model will use the generation_config.json from the repo by default
# You can also override parameters here
outputs = model.diffusion_generate(
    inputs=input_ids,
    max_new_tokens=100,
    steps=16,
    temperature=0.8
)

# Decode the output
prompt_len = input_ids.shape[1]
generated_text = tokenizer.decode(outputs.sequences[0][prompt_len:], skip_special_tokens=True)

print("--- Generated Code ---")
print(generated_text)

Citation

@misc{opendllm2025,
  title        = {Open-dLLM: Open Diffusion Large Language Models},
  author       = {Fred Zhangzhi Peng, Shuibai Zhang, Alex Tong, and contributors},
  year         = {2025},
  howpublished = {\url{https://github.com/pengzhangzhi/Open-dLLM}},
  note         = {Blog: \url{https://oval-shell-31c.notion.site/Open-Diffusion-Large-Language-Model-25e03bf6136480b7a4ebe3d53be9f68a?pvs=74}, 
                  Model: \url{https://huggingface.co/fredzzp/open-dcoder-0.5B}}
}