Instructions to use aungkomyint/tara10m-sft-v1-2k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aungkomyint/tara10m-sft-v1-2k with Transformers:

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

pipe = pipeline("text-generation", model="aungkomyint/tara10m-sft-v1-2k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("aungkomyint/tara10m-sft-v1-2k")
model = AutoModelForMultimodalLM.from_pretrained("aungkomyint/tara10m-sft-v1-2k")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aungkomyint/tara10m-sft-v1-2k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aungkomyint/tara10m-sft-v1-2k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aungkomyint/tara10m-sft-v1-2k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aungkomyint/tara10m-sft-v1-2k

SGLang

How to use aungkomyint/tara10m-sft-v1-2k 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 "aungkomyint/tara10m-sft-v1-2k" \
    --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": "aungkomyint/tara10m-sft-v1-2k",
		"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 "aungkomyint/tara10m-sft-v1-2k" \
        --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": "aungkomyint/tara10m-sft-v1-2k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aungkomyint/tara10m-sft-v1-2k with Docker Model Runner:
```
docker model run hf.co/aungkomyint/tara10m-sft-v1-2k
```

Tara10M SFT v1 2K

Tara10M SFT v1 2K is a small 10.4M parameter Burmese-English causal language model exported in Hugging Face Llama-compatible format.

This is a learning/school-project model. It is not a production assistant.

Model Details

Architecture: Llama-style decoder-only causal LM
Parameters: 10,390,784
Layers: 6
Hidden size: 256
Attention heads: 4
Vocabulary: 16,000 SentencePiece tokens
Context length: 1,024
Base checkpoint: Tara10M Colab base checkpoint
SFT data: 2,000 cleaned synthetic Burmese-English instruction examples

Intended Use

Best test areas:

short English to Burmese translation
short Burmese to English translation
simple Burmese rewrite
travel phrasebook style prompts

Prompt format:

Instruction: Translate this sentence to Burmese.
Input: I will go home tomorrow.
Response:

Limitations

This model is very small and still repeats, drifts, and gives wrong translations. It should be used for experimentation only.

Known issues:

weak factual reliability
repeated phrases
mixed Burmese/English output
poor long-form generation
not suitable for safety-critical use

Training Summary

SFT examples: 2,000
Train examples: 1,800
Validation examples: 200
Max steps: 400
Learning rate: 2e-5
Best validation loss: 2.4228

Files

model.safetensors
config.json
tokenizer.model
tokenizer_config.json
special_tokens_map.json

Downloads last month: 26

Safetensors

Model size

10.4M params

Tensor type

F32

Model tree for aungkomyint/tara10m-sft-v1-2k

Finetunes

1 model