Panini-00 50M

Hindi ↔ Sanskrit sentence translation in Devanagari. Custom PyTorch checkpoint, not a Transformers model.

Files

File Role
checkpoint.pt Model weights
tokenizer.model SentencePiece tokenizer, 32,000 pieces

Keep this tokenizer with this checkpoint. It does not match Panini-00 10M or Panini-00 18M.

Tasks

Task Direction
translate_hi_sa Hindi → Sanskrit
translate_sa_hi Sanskrit → Hindi
sanskritize_hindi Hindi with Sanskrit words
correct_hi Hindi grammar and word choice
correct_sa Sanskrit grammar

Pass one Devanagari sentence. The loader adds the task tags.

Examples

Task Prompt Example
sanskritize_hindi मैं स्कूल जाता हूँ और पानी पीता हूँ। मैं विद्यालय जाता हूँ और जल पीता हूँ।
sanskritize_hindi यह किताब बहुत अच्छी है। यह पुस्तक अति उत्तम है।
correct_hi यह पुस्तक अच्छा है। यह पुस्तक अच्छी है।
correct_hi वह किताब पढ़ता हैं। वह किताब पढ़ता है।
correct_sa अहं गृहं गच्छति। अहं गृहं गच्छामि।
correct_sa बालकः पुस्तकं पठन्ति। बालकः पुस्तकं पठति।
translate_hi_sa मैं किताब पढ़ता हूँ। अहं पुस्तकं पठामि।

Size

Parameters 50,476,544
Layers 13
Width 512
Query / key-value heads 8 / 2
Head dimension 64
Feed-forward width 1,280
Context 1,024 tokens
Vocabulary 32,000
Pretrain tokens 500,009,664
Supervised tokens 20,000,534
Supervised examples 312,176

Install

Reference code: midroid/ai-models, branch experiment/010-hindi-sanskrit. Python 3.10+, PyTorch, SentencePiece, and PyYAML.

git clone --branch experiment/010-hindi-sanskrit --depth 1 https://github.com/midroid/ai-models.git
cd ai-models/experiments/language/010-hindi-sanskrit-slm
uv sync
huggingface-cli download akashchauhan/panini-00-50m --local-dir weights/panini-00-50m

Inference

Greedy decoding (temperature 0). Generation stops at end-of-sequence and cannot pass the 1,024-token context, including the prompt.

uv run python -m src.sample \
  --checkpoint weights/panini-00-50m \
  --task sanskritize_hindi \
  --prompt "मैं स्कूल जाता हूँ और पानी पीता हूँ।" \
  --max-new-tokens 32

The result is the text after <tgt>. correct_hi and correct_sa use the same command with a different --task. CPU is sufficient.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support