---
title: JanusCoder-14B
canonical_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/JanusCoder-14B"
md_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/JanusCoder-14B.md"
repository: Shanghai_AI_Laboratory/JanusCoder-14B
last_updated: 2025-11-09
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3
architectures:
  - Qwen3ForCausalLM
parameters: 14.8B
tensor_type:
  - BF16
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 165
stars: 1
---

# JanusCoder-14B

> JanusCoder-14B - Shanghai_AI_Laboratory 在 ModelScope 开源的模型。💻Github Repo • 🤗Model Collections • 📜Technical Report

Shanghai_AI_Laboratory/JanusCoder-14B 是 ModelScope 魔搭社区上的 14.8B 参数text-generation模型，采用 apache-2.0 许可，可用 deploy_task text/emb、lmdeploy_turbomind 0.9.1、sglang 0.5.2 部署。

- **Repository**: Shanghai_AI_Laboratory/JanusCoder-14B
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 14.8B
- **Inference backends**: deploy_task text/emb, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Downloads**: 165
- **Stars**: 1
- **Last updated**: 2025-11-09

Source: https://www.modelscope.cn/models/Shanghai_AI_Laboratory/JanusCoder-14B

---

# JanusCoder-14B

[💻Github Repo](https://github.com/InternLM/JanusCoder) • [🤗Model Collections](https://huggingface.co/collections/internlm/januscoder) • [📜Technical Report](https://www.arxiv.org/abs/2510.23538)

## 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

| Model Name | Description | Download |
| --- | --- | --- |
| JanusCoder-8B | 8B text model based on Qwen3-8B. | 🤗 [Model](https://huggingface.co/internlm/JanusCoder-8B) |
| 👉 **JanusCoder-14B** | 14B text model based on Qwen3-14B. | 🤗 [Model](https://huggingface.co/internlm/JanusCoder-14B) |
| JanusCoderV-7B | 7B multimodal model based on Qwen2.5-VL-7B. | 🤗 [Model](https://huggingface.co/internlm/JanusCoderV-7B) |
| JanusCoderV-8B | 8B multimodal model based on InternVL3.5-8B. | 🤗 [Model](https://huggingface.co/internlm/JanusCoderV-8B) |

## Performance

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

| Model | JanusCoder-14B | Qwen3-14B | Qwen2.5-Coder-32B-Instruct | LLaMA3-8B-Instruct | GPT-4o |
| --- | --- | --- | --- | --- | --- |
| PandasPlotBench (Task) | 86 | 78 | 82 | 69 | 85 |
| ArtifactsBench | 41.1 | 36.5 | 35.5 | 36.5 | 37.9 |
| DTVBench (Manim) | 8.41 | 6.63 | 9.61 | 4.92 | 10.60 |
| DTVBench (Wolfram) | 5.97 | 5.08 | 4.98 | 3.15 | 5.97 |

## 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.

```python
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "internlm/JanusCoder-14B"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, device_map="auto", dtype="auto",
).eval()

messages = [
    {"role": "user", "content": "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)

with torch.inference_mode():
    generate_ids = model.generate(**inputs, max_new_tokens=200)
    decoded_output = tokenizer.batch_decode(generate_ids, skip_special_tokens=True)

print(decoded_output[0])
```

## 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:

```bibtex
@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}
}
```