README.md

metadata

license: mit
language:
  - sa
  - en
tags:
  - sanskrit
  - paraphrase
  - diffusion
  - d3pm
  - pytorch
pipeline_tag: text2text-generation

Sanskrit D3PM Paraphrase Model

Roman/IAST Sanskrit input to Devanagari output using a D3PM cross-attention model.

Files Included

• best_model.pt — trained checkpoint
• config.py — runtime config
• inference.py — model loading + generation loop
• inference_api.py — simple Python API (predict)
• handler.py — Hugging Face Endpoint handler
• model/, diffusion/ — architecture modules
• sanskrit_src_tokenizer.json, sanskrit_tgt_tokenizer.json — tokenizers

Quick Local Test

from inference_api import predict
print(predict("dharmo rakṣati rakṣitaḥ")["output"])

Transformer-Style Usage (Custom Runtime)

This checkpoint is a custom D3PM architecture (.pt), not a native transformers AutoModel format. Use it in a transformer-like way via the provided runtime:

import torch
from config import CONFIG
from inference import load_model, run_inference, _decode_clean
from model.tokenizer import SanskritSourceTokenizer, SanskritTargetTokenizer

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model, cfg = load_model("best_model.pt", CONFIG, device)

src_tok = SanskritSourceTokenizer(vocab_size=16000, max_len=cfg["model"]["max_seq_len"])
tgt_tok = SanskritTargetTokenizer(vocab_size=16000, max_len=cfg["model"]["max_seq_len"])

text = "dharmo rakṣati rakṣitaḥ"
ids = torch.tensor([src_tok.encode(text)], dtype=torch.long, device=device)
out = run_inference(model, ids, cfg)
print(_decode_clean(tgt_tok, out[0].tolist()))

If you need full transformers compatibility (AutoModel.from_pretrained), export weights to a Hugging Face Transformers model format first.

Endpoint Payload

{
  "inputs": "yadā mano nivarteta viṣayebhyaḥ svabhāvataḥ",
  "parameters": {
    "temperature": 0.7,
    "top_k": 40,
    "repetition_penalty": 1.2,
    "diversity_penalty": 0.0,
    "num_steps": 64,
    "clean_output": true
  }
}

Push This Folder To Model Hub

huggingface-cli login
huggingface-cli repo create <your-username>/sanskrit-d3pm --type model
cd hf_model_repo
git init
git lfs install
git remote add origin https://huggingface.co/<your-username>/sanskrit-d3pm
git add .
git commit -m "Initial model release"
git push -u origin main