Instructions to use Veda-Labs/Vedika-Code-Pro-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Veda-Labs/Vedika-Code-Pro-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Veda-Labs/Vedika-Code-Pro-v1", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Veda-Labs/Vedika-Code-Pro-v1", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Veda-Labs/Vedika-Code-Pro-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Veda-Labs/Vedika-Code-Pro-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Veda-Labs/Vedika-Code-Pro-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Veda-Labs/Vedika-Code-Pro-v1

SGLang

How to use Veda-Labs/Vedika-Code-Pro-v1 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 "Veda-Labs/Vedika-Code-Pro-v1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Veda-Labs/Vedika-Code-Pro-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Veda-Labs/Vedika-Code-Pro-v1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Veda-Labs/Vedika-Code-Pro-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Veda-Labs/Vedika-Code-Pro-v1 with Docker Model Runner:
```
docker model run hf.co/Veda-Labs/Vedika-Code-Pro-v1
```

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

Downloads last month: 52

Safetensors

Model size

812B params

Tensor type

BF16

I64

F32

F8_E4M3