Instructions to use senthil090/tamil-tiny-stories with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use senthil090/tamil-tiny-stories with Transformers:

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

pipe = pipeline("text-generation", model="senthil090/tamil-tiny-stories", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("senthil090/tamil-tiny-stories", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use senthil090/tamil-tiny-stories with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "senthil090/tamil-tiny-stories"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "senthil090/tamil-tiny-stories",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/senthil090/tamil-tiny-stories

SGLang

How to use senthil090/tamil-tiny-stories 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 "senthil090/tamil-tiny-stories" \
    --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": "senthil090/tamil-tiny-stories",
		"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 "senthil090/tamil-tiny-stories" \
        --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": "senthil090/tamil-tiny-stories",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use senthil090/tamil-tiny-stories with Docker Model Runner:
```
docker model run hf.co/senthil090/tamil-tiny-stories
```

Tamil Tiny Stories

A Toy model to generate character level stories in Tamil.

Model details

Architecture: custom decoder-only transformer
Tokenization: character-level
Training data source: neuralnets/multilingual-tinystories Tamil split (ta)

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "senthil090/tamil-tiny-stories"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_id, trust_remote_code=True)

inputs = tokenizer("ஒரு நாள்", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 18

Safetensors

Model size

1.19M params

Tensor type

F32

senthil090
/

tamil-tiny-stories

Tamil Tiny Stories

Model details

Usage

Dataset used to train senthil090/tamil-tiny-stories