GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
fredzzp
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
fredzzp
Model Tree
Input Modalities
Output Modalities
Supported Functionality
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.
This model uses bidirectional attention and must be used with the custom diffusion_generate method.
First, make sure you have the latest transformers library installed.
bash
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.
python
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMmodel_id = "fredzzp/open-dcoder-0.5B"device = "cuda" if torch.cuda.is_available() else "cpu"# trust_remote_code=True is essentialtokenizer = 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 hereoutputs = model.diffusion_generate(inputs=input_ids,max_new_tokens=100,steps=16,temperature=0.8)# Decode the outputprompt_len = input_ids.shape[1]generated_text = tokenizer.decode(outputs.sequences[0][prompt_len:], skip_special_tokens=True)print("--- Generated Code ---")print(generated_text)