| """Minimal inference example for TinyTurk v2.7d.""" | |
| import torch | |
| import sentencepiece as spm | |
| from huggingface_hub import hf_hub_download | |
| from model import TinyTurkGPTV27, TinyTurkV27Config | |
| REPO = "stunmuffin/TinyTurk-v2.7d" | |
| ckpt_path = hf_hub_download(REPO, "pytorch_model.bin") | |
| tok_path = hf_hub_download(REPO, "tokenizer_v11_bpe_512.model") | |
| ckpt = torch.load(ckpt_path, map_location="cpu") | |
| config = TinyTurkV27Config(**ckpt["config"]) | |
| model = TinyTurkGPTV27(config) | |
| model.load_state_dict(ckpt["model_state_dict"]) | |
| model.eval() | |
| sp = spm.SentencePieceProcessor(model_file=tok_path) | |
| for prompt in ["Ali elmayi", "Bir sabah", "Kucuk kedi"]: | |
| ids = [sp.bos_id()] + sp.encode(prompt, out_type=int) | |
| input_ids = torch.tensor([ids]) | |
| with torch.no_grad(): | |
| out = model.generate(input_ids, max_new_tokens=40, | |
| temperature=0.8, top_k=40) | |
| print("PROMPT:", prompt) | |
| print("OUTPUT:", sp.decode(out[0].tolist())) | |
| print("-" * 60) | |