Harley-ml/TinyWord2-128k

wrtervulatoration

appatating

ay's

aceae

# =============================================================================
# Inference
# =============================================================================

MODEL_DIR      = "Harley-ml/TinyWord2-128k"   # path
TOKENIZER_PATH = "Harley-ml/TinyWord2-128k"

# --- Generation settings ---
PROMPT             = "w"   # prompt
MAX_NEW_TOKENS     = 32
TEMPERATURE        = 1.2
TOP_P              = 0.95
TOP_K              = 50
REPETITION_PENALTY = 1.1
DO_SAMPLE          = True

# =============================================================================

import torch
from pathlib import Path
from transformers import (
    AutoModelForCausalLM,
    PreTrainedTokenizerFast,
    AddedToken,
)

# ---------------------------------------------------------------------------
# Device
# ---------------------------------------------------------------------------

device = (
    "cuda" if torch.cuda.is_available() else
    "mps"  if torch.backends.mps.is_available() else
    "cpu"
)
print(f"Device : {device}")

# ---------------------------------------------------------------------------
# Tokenizer  (mirrors training setup)
# ---------------------------------------------------------------------------

def load_tokenizer(path: str):
    p = Path(path).resolve()
    if not p.exists():
        raise FileNotFoundError(f"Tokenizer not found: {p}")
    tok = PreTrainedTokenizerFast(tokenizer_file=str(p))
    specials = {}
    if tok.bos_token is None: specials["bos_token"] = AddedToken("<|bos|>", special=True)
    if tok.eos_token is None: specials["eos_token"] = AddedToken("<|eos|>", special=True)
    if tok.unk_token is None: specials["unk_token"] = AddedToken("<|unk|>", special=True)
    if tok.pad_token is None:
        if tok.eos_token is not None:
            tok.pad_token = tok.eos_token
        else:
            specials["pad_token"] = AddedToken("<|pad|>", special=True)
    if specials:
        tok.add_special_tokens(specials)
    tok.padding_side = "left"  # left-pad for batched generation
    return tok

print("Loading tokenizer...")
tokenizer = load_tokenizer(TOKENIZER_PATH)
print(f"  Vocab size : {tokenizer.vocab_size}")
print(f"  BOS        : {tokenizer.bos_token!r}")
print(f"  EOS        : {tokenizer.eos_token!r}")
print(f"  PAD        : {tokenizer.pad_token!r}  (id={tokenizer.pad_token_id})")

# ---------------------------------------------------------------------------
# Model
# ---------------------------------------------------------------------------

print(f"\nLoading model from {MODEL_DIR} ...")
model = AutoModelForCausalLM.from_pretrained(
    MODEL_DIR,
    dtype=torch.float16 if device == "cuda" else torch.float32,
    low_cpu_mem_usage=True,
)
model.eval()
model.to(device)

total_params = sum(p.numel() for p in model.parameters())
print(f"  Parameters : {total_params:,}")

# ---------------------------------------------------------------------------
# Generation helper
# ---------------------------------------------------------------------------

def generate(
    prompt: str             = PROMPT,
    max_new_tokens: int     = MAX_NEW_TOKENS,
    temperature: float      = TEMPERATURE,
    top_p: float            = TOP_P,
    top_k: int              = TOP_K,
    repetition_penalty: float = REPETITION_PENALTY,
    do_sample: bool         = DO_SAMPLE,
) -> str:
    
    bos         = tokenizer.bos_token or ""
    full_prompt = bos + prompt

    inputs = tokenizer(
        full_prompt,
        return_tensors="pt",
        add_special_tokens=False,
    ).to(device)
    inputs.pop("token_type_ids", None)  # Qwen3 doesn't use this

    gen_kwargs = dict(
        max_new_tokens     = max_new_tokens,
        do_sample          = do_sample,
        repetition_penalty = repetition_penalty,
        eos_token_id       = tokenizer.eos_token_id,
        pad_token_id       = tokenizer.pad_token_id,
    )
    if do_sample:
        gen_kwargs["temperature"] = temperature
        gen_kwargs["top_p"]       = top_p
        gen_kwargs["top_k"]       = top_k

    with torch.inference_mode():
        output_ids = model.generate(**inputs, **gen_kwargs)

    # Strip the prompt tokens so we only return what was generated
    prompt_len = inputs["input_ids"].shape[-1]
    new_ids    = output_ids[0][prompt_len:]
    return tokenizer.decode(new_ids, skip_special_tokens=True)


# ---------------------------------------------------------------------------
# Run
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    print(f"\nPrompt : {PROMPT!r}")
    print("-" * 60)

    output = generate(PROMPT)

    print("Generated:")
    print(output)

@misc{tinyword2-128k,
  title     = {TinyWord-134k: A Test of Morphological Compression in TLMs},
  author    = {Harley-ml},
  year      = {2026},
  url       = {https://huggingface.co/Harley-ml/TinyWord2-128k}
}