JanusCoder-14B-AWQ-4bit

JanusCoder-14B AWQ - INT4

Model Details

Quantization Details

• Quantization Method: AWQ
• Bits: 4
• Group Size: 32
• Calibration Dataset: nvidia/Llama-Nemotron-Post-Training-Dataset
• Quantization Tool: llm-compressor

Get Started

Prerequisite

pip install -U vllm

Basic Usage

vllm serve cyankiwi/JanusCoder-14B-AWQ-4bit

Additional Information

Changelog

• v1.0.0 - Initial quantized release

Authors

• Name: cyankiwi

• Contacts: [email protected]

JanusCoder-14B

💻Github Repo • 🤗Model Collections • 📜Technical Report

Introduction

We introduce JanusCoder and JanusCoderV, a suite of open-source foundational models designed to establish a unified visual-programmatic interface for code intelligence. This model suite is built upon open-source language models (such as Qwen3-8B and 14B) and multimodal models (such as Qwen2.5-VL and InternVL3.5-8B). The JanusCoder series is trained on JANUSCODE-800K—the largest multimodal code corpus to date, generated by an innovative synthesis toolkit, covering everything from standard charts to complex interactive Web UIs and code-driven animations. This enables the models to uniformly handle diverse visual-programmatic tasks, such as generating code from textual instructions, visual inputs, or a combination of both, rather than building specialized models for isolated tasks. JanusCoder excels at flexible content generation (like data visualizations and interactive front-ends) as well as precise, program-driven editing of visual effects and complex animation construction.

Model Downloads

Performance

We evaluate the JanusCoder model on various benchmarks that span code interlligence tasks on multiple PLs:

Quick Start

Transformers

The following provides demo code illustrating how to generate text using JanusCoder-14B.

Please use transformers >= 4.55.0 to ensure the model works normally.

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "internlm/JanusCoder-14B"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto")

messages = [
    {
        "role": "user",
        "content": [
            {"type": "text", "text": "Create a line plot that illustrates function y=x."},
        ],
    }
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt").to(model.device, dtype=torch.bfloat16)

generate_ids = model.generate(**inputs, max_new_tokens=32768)
decoded_output = processor.decode(generate_ids[0, inputs["input_ids"].shape[1] :], skip_special_tokens=True)
print(decoded_output)

Citation

🫶 If you are interested in our work or find the repository / checkpoints / benchmark / data helpful, please consider using the following citation format when referencing our papers:

@article{sun2025januscoder,
  title={JanusCoder: Towards a Foundational Visual-Programmatic Interface for Code Intelligence},
  author={Sun, Qiushi and Gong, Jingyang and Liu, Yang and Chen, Qiaosheng and Li, Lei and Chen, Kai and Guo, Qipeng and Kao, Ben and Yuan, Fei},
  journal={arXiv preprint arXiv:2510.23538},
  year={2025}
}

@article{sun2024survey,
  title={A survey of neural code intelligence: Paradigms, advances and beyond},
  author={Sun, Qiushi and Chen, Zhirui and Xu, Fangzhi and Cheng, Kanzhi and Ma, Chang and Yin, Zhangyue and Wang, Jianing and Han, Chengcheng and Zhu, Renyu and Yuan, Shuai and others},
  journal={arXiv preprint arXiv:2403.14734},
  year={2024}
}

@article{chen2025interactscience,
  title={InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation},
  author={Chen, Qiaosheng and Liu, Yang and Li, Lei and Chen, Kai and Guo, Qipeng and Cheng, Gong and Yuan, Fei},
  journal={arXiv preprint arXiv:2510.09724},
  year={2025}
}

@article{sun2025codeevo,
  title={CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback},
  author={Sun, Qiushi and Gong, Jinyang and Li, Lei and Guo, Qipeng and Yuan, Fei},
  journal={arXiv preprint arXiv:2507.22080},
  year={2025}
}