File size: 2,417 Bytes
7d6a683 ad411a1 7d6a683 ad411a1 0ffbe78 7d6a683 0ffbe78 ad411a1 0ffbe78 ad411a1 0ffbe78 ad411a1 0ffbe78 ad411a1 0ffbe78 5a5ac8a 0ffbe78 ad411a1 0ffbe78 ad411a1 7d6a683 ad411a1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 | ---
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
```python
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:
```python
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
```json
{
"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
```bash
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
```
|