Instructions to use sky-2002/Marathi-SmolLM2-145M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sky-2002/Marathi-SmolLM2-145M with Transformers:

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

pipe = pipeline("text-generation", model="sky-2002/Marathi-SmolLM2-145M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sky-2002/Marathi-SmolLM2-145M")
model = AutoModelForCausalLM.from_pretrained("sky-2002/Marathi-SmolLM2-145M")
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

vLLM

How to use sky-2002/Marathi-SmolLM2-145M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sky-2002/Marathi-SmolLM2-145M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sky-2002/Marathi-SmolLM2-145M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sky-2002/Marathi-SmolLM2-145M

SGLang

How to use sky-2002/Marathi-SmolLM2-145M 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 "sky-2002/Marathi-SmolLM2-145M" \
    --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": "sky-2002/Marathi-SmolLM2-145M",
		"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 "sky-2002/Marathi-SmolLM2-145M" \
        --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": "sky-2002/Marathi-SmolLM2-145M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use sky-2002/Marathi-SmolLM2-145M with Docker Model Runner:
```
docker model run hf.co/sky-2002/Marathi-SmolLM2-145M
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

Model Details

An experimental 145M parameter pre-trained base model for marathi. Inspired by SmolLM2 and its architecture.

Pre-trained on verified marathi split of the ai4bharat/sangraha dataset, around ~2.8 billion tokens.

Note: This is an experimental model and will be followed by more pre-training, followed by task specific instruction finetuning.

How to use

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sky-2002/Marathi-SmolLM2-145M")
model = AutoModelForCausalLM.from_pretrained("sky-2002/Marathi-SmolLM2-145M")

sentence = "पुणे विद्यापीठाने म्हटले आहे"
inputs = tokenizer(sentence, return_tensors="pt")
output = model.generate(**inputs, max_length=50)
print(tokenizer.batch_decode(output, skip_special_tokens=True))

Model Description, data and training details

Architecture: SmolLM2 based

Tokenizer: Uses the sarvamai/sarvam-1 tokenizer, since it has been trained on indic languages and has lower fertility rates than existing multilingual tokenizers.

Training dataset: The training dataset covers the following domains.

Training:

Trained using modal platform on an A100.
Trained for 1 epoch on verified marathi split of sangraha dataset, covering ~5.8M samples.

This model can generate coherent text, especially in the domains similar to those in the training dataset.

Bias, Risks, and Limitations

This model is trained on data of 2.8 B tokens and using a context length of 512, due to computational constraints of training. Often gives out gibberish if prompt is not related to domains shown, or if in a conversational style.