Instructions to use SauravMahalik/kalinga-01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SauravMahalik/kalinga-01 with Transformers:

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

pipe = pipeline("text-generation", model="SauravMahalik/kalinga-01")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SauravMahalik/kalinga-01")
model = AutoModelForCausalLM.from_pretrained("SauravMahalik/kalinga-01", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use SauravMahalik/kalinga-01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SauravMahalik/kalinga-01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SauravMahalik/kalinga-01",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SauravMahalik/kalinga-01

SGLang

How to use SauravMahalik/kalinga-01 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 "SauravMahalik/kalinga-01" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SauravMahalik/kalinga-01",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "SauravMahalik/kalinga-01" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SauravMahalik/kalinga-01",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SauravMahalik/kalinga-01 with Docker Model Runner:
```
docker model run hf.co/SauravMahalik/kalinga-01
```

🏛️ KALINGA — Experiment No. 01

One language. Done properly.

The frontier forgot Odia.

40+ million speakers. A literary tradition older than most languages the frontier has ever shipped. And the biggest labs in the world trained on 200 languages — and left this one out, as if it had never existed.

Kalinga exists because we refuse to accept that.

This is Experiment No. 01. The first of a series that will not stop.

What we found, and what we kept

We started with 28,549,762 rows of raw Odia.

More than half of it was the same text wearing different clothes. We removed it all. What remains is signal — and nothing else:


Rows kept	12,438,948 — nothing repeated, nothing padded
Total text	~5.9 billion characters of Odia
English-aligned	48.7 % — real alignments, not flags
Per-row	median 203 · mean 474 characters
Quality gate	≥ 20 chars · ≥ 10 % Odia script · 63 shards · 3.7 GB
Composition	monolingual 68.9 % · pretrain 15.4 % · parallel 7.7 % · instruction 5.3 % · QA 1.5 % · web · encyclopedic · speech · sentiment

The frontier's approach: 200 languages, two minutes each.

Kalinga's approach: one language, 5.9 billion characters, nothing repeated.

The corpus has never been published anywhere. While licensing of legacy sources is resolved, it stays private — this model is the closest thing to it that exists in public.

The confession

We have no eval numbers. We will not invent any.

Hype without receipts dies. Kalinga is not here to die.

When the numbers exist, they will be written here — and this page will change forever. What you are looking at right now is the model before it had a reputation. That window never reopens.

Status

Exists
Remembers its language
Evaluated — soon. then this card gets real.
Explained
Named — you'll recognize it when you see it.
Freed — the corpus, when licensing allows.

Watch. The silence will not last.

For the 40 million

Your language was never the problem. The attention was.

It's free. Take it. Use it. That's the point.

If you must:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "SauravMahalik/kalinga-01"

model = AutoModelForCausalLM.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)

text = "..."  # a sentence, in a language it knows
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=64)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

— Experiment No. 01 · Kalinga Series

The series has already begun.

Downloads last month: 24

Safetensors

Model size

3B params

Tensor type

F32