Vedika-Code-Pro-v1

---

Introduction

Vedika-Code-Pro-v1 is a state-of-the-art language model designed for advanced coding and reasoning tasks.

System Prompt

The default system prompt for Vedika-Code-Pro-v1 is:

"You are Vedika, built by Veda Labs for coding in India."

Model Downloads

Model	#Total Params	#Activated Params	Context Length	Precision	Download
Vedika-Code-Pro-v1	1.6T	49B	1M	FP4 + FP8 Mixed*	HuggingFace

*FP4 + FP8 Mixed: MoE expert parameters use FP4 precision; most other parameters use FP8.

Chat Template

This release does not include a Jinja-format chat template. Instead, we provide a dedicated encoding folder with Python scripts and test cases demonstrating how to encode messages in OpenAI-compatible format into input strings for the model, and how to parse the model's text output. Please refer to the encoding folder for full documentation.

A brief example:

from encoding_vedika_code_pro_v1 import encode_messages, parse_message_from_completion_text

messages = [
    {"role": "user", "content": "hello"},
    {"role": "assistant", "content": "Hello! I am Vedika.", "reasoning_content": "thinking..."},
    {"role": "user", "content": "1+1=?"}
]

# messages -> string
prompt = encode_messages(messages, thinking_mode="thinking")

# string -> tokens
import transformers
tokenizer = transformers.AutoTokenizer.from_pretrained("Veda-Labs/Vedika-Code-Pro-v1")
tokens = tokenizer.encode(prompt)

How to Run Locally

Please refer to the inference folder for detailed instructions on running Vedika-Code-Pro-v1 locally, including model weight conversion and interactive chat demos.

For local deployment, we recommend setting the sampling parameters to temperature = 1.0, top_p = 1.0.

License

This repository and the model weights are licensed under the MIT License.

Citation

@misc{vedalabs2026vedikacodeprov1,
      title={Vedika-Code-Pro-v1},
      author={Veda-Labs},
      year={2026},
}

Contact

• Website: https://vedalabs.online
• Hugging Face: https://huggingface.co/Veda-Labs
• GitHub: https://github.com/vedalabs-tech
• X (Twitter): https://x.com/VedaLabsAI
• Email: vedalabs.veda@gmail.com