MyanmarTranslator-210M-Pro is a 210.90M-parameter bidirectional English ↔ Burmese (en ↔ my) neural machine translation model built on a custom 8-Layer Bidirectional Encoder + 8-Layer Cross-Attentive Decoder Transformer architecture. It was warm-started via All-Layer Net2Wider + Net2Deeper expansion from MyanmarTranslator-84M-Base and trained on HuggingFaceFW/finetranslations.
1.6724 (Val PPL: 5.33)bfloat16 (model.safetensors)65,664 vocab, tokenizer.model)training_codes.txt & trainingcelloutputwitheval.txt| Component | Specification |
|---|---|
| Architecture | Custom Encoder-Decoder Transformer |
| Parameters | 210.90M |
| Encoder / Decoder Layers | 8 Encoder + 8 Decoder |
Hidden Size (d_model) |
768 |
Attention Heads (n_heads) |
12 (head_dim = 64) |
Feed-Forward (ffn_dim) |
2816 (SwiGLU) |
| Normalization | RMSNorm (eps=1e-6, Pre-Norm + QK-Norm) |
| Positional Encoding | Rotary Position Embeddings (RoPE, theta=10000.0, max_seq_len=1024) |
| Vocabulary Size | 65,664 (Tied embed_tokens & lm_head, scaled by √d_model) |
| Special Control Tokens | UNK=0, BOS=1, EOS=2, PAD=3, <2my>=65536, <2en>=65537 |
pip install -U torch sentencepiece safetensors huggingface_hub numpy pyarrow datasets
my ↔ en)The standalone PyTorch + SentencePiece implementation below uses pre-allocated KV-caching, PyTorch SDPA (FlashAttention / Memory-Efficient Attention), dynamic active-sequence pruning, and Burmese Unicode normalization + clause-aware chunking for long text.
import math
import os
import re
import numpy as np
import sentencepiece as spm
import torch
import torch.nn as nn
import torch.nn.functional as F
from huggingface_hub import snapshot_download
from safetensors.torch import load_file
MODEL_REPO = "freococo/MyanmarTranslator-210M-Pro"
MODEL_DIR = snapshot_download(
repo_id=MODEL_REPO,
ignore_patterns=["checkpoint-*/*", "*.pt", "*.txt"],
)
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")
COMPUTE_DTYPE = (
torch.bfloat16
if (torch.cuda.is_available() and torch.cuda.get_device_capability()[0] >= 8)
else (torch.float16 if torch.cuda.is_available() else torch.float32)
)
VOCAB_SIZE, UNK_ID, BOS_ID, EOS_ID, PAD_ID = 65664, 0, 1, 2, 3
TOK_2MY, TOK_2EN = 65536, 65537
class RMSNorm(nn.Module):
def __init__(self, dim: int, eps: float = 1e-6):
super().__init__()
self.dim, self.eps = (dim,), eps
self.weight = nn.Parameter(torch.ones(dim))
def forward(self, x: torch.Tensor) -> torch.Tensor:
return F.rms_norm(x, self.dim, self.weight, self.eps)
class RotaryEmbedding(nn.Module):
def __init__(self, dim: int, max_seq_len: int = 1024, theta: float = 10000.0):
super().__init__()
inv_freq = 1.0 / (theta ** (torch.arange(0, dim, 2, dtype=torch.float32) / dim))
t = torch.arange(max_seq_len, dtype=torch.float32)
freqs = torch.outer(t, inv_freq)
self.register_buffer("cos_cached", freqs.cos()[None, None, :, :], persistent=False)
self.register_buffer("sin_cached", freqs.sin()[None, None, :, :], persistent=False)
def forward(self, x: torch.Tensor) -> torch.Tensor:
L = x.size(2)
cos, sin = self.cos_cached[:, :, :L, :], self.sin_cached[:, :, :L, :]
x1, x2 = x[..., ::2], x[..., 1::2]
return torch.cat((x1 * cos - x2 * sin, x1 * sin + x2 * cos), dim=-1)
class SwiGLU(nn.Module):
def __init__(self, d_model: int, ffn_dim: int):
super().__init__()
self.gate_up = nn.Linear(d_model, 2 * ffn_dim, bias=False)
self.down = nn.Linear(ffn_dim, d_model, bias=False)
def forward(self, x: torch.Tensor) -> torch.Tensor:
gate, up = self.gate_up(x).chunk(2, dim=-1)
return self.down(F.silu(gate) * up)
class SelfAttention(nn.Module):
def __init__(self, d_model: int, n_heads: int, is_causal: bool = False):
super().__init__()
self.n_heads, self.head_dim, self.is_causal = n_heads, d_model // n_heads, is_causal
self.qkv = nn.Linear(d_model, 3 * d_model, bias=False)
self.out = nn.Linear(d_model, d_model, bias=False)
self.q_norm, self.k_norm = RMSNorm(self.head_dim), RMSNorm(self.head_dim)
def forward(self, x: torch.Tensor, rope: RotaryEmbedding, attn_mask: torch.Tensor = None) -> torch.Tensor:
B, L, D = x.shape
q, k, v = self.qkv(x).chunk(3, dim=-1)
q = self.q_norm(q.view(B, L, self.n_heads, self.head_dim).transpose(1, 2))
k = self.k_norm(k.view(B, L, self.n_heads, self.head_dim).transpose(1, 2))
v = v.view(B, L, self.n_heads, self.head_dim).transpose(1, 2)
q, k = rope(q), rope(k)
y = F.scaled_dot_product_attention(
q, k, v, attn_mask=None if self.is_causal else attn_mask, is_causal=self.is_causal
)
return self.out(y.transpose(1, 2).reshape(B, L, D))
def step_kv(self, x_step, cos_p, sin_p, pos, k_cache, v_cache) -> torch.Tensor:
B, _, D = x_step.shape
q, k, v = self.qkv(x_step).chunk(3, dim=-1)
q = self.q_norm(q.view(B, 1, self.n_heads, self.head_dim).transpose(1, 2))
k = self.k_norm(k.view(B, 1, self.n_heads, self.head_dim).transpose(1, 2))
v = v.view(B, 1, self.n_heads, self.head_dim).transpose(1, 2)
q1, q2 = q[..., ::2], q[..., 1::2]
k1, k2 = k[..., ::2], k[..., 1::2]
q = torch.cat((q1 * cos_p - q2 * sin_p, q1 * sin_p + q2 * cos_p), dim=-1)
k = torch.cat((k1 * cos_p - k2 * sin_p, k1 * sin_p + k2 * cos_p), dim=-1)
k_cache[:, :, pos : pos + 1, :] = k
v_cache[:, :, pos : pos + 1, :] = v
y = F.scaled_dot_product_attention(
q, k_cache[:, :, : pos + 1, :], v_cache[:, :, : pos + 1, :], is_causal=False
)
return self.out(y.transpose(1, 2).reshape(B, 1, D))
class CrossAttention(nn.Module):
def __init__(self, d_model: int, n_heads: int):
super().__init__()
self.n_heads, self.head_dim = n_heads, d_model // n_heads
self.q_proj = nn.Linear(d_model, d_model, bias=False)
self.kv_proj = nn.Linear(d_model, 2 * d_model, bias=False)
self.out = nn.Linear(d_model, d_model, bias=False)
self.q_norm, self.k_norm = RMSNorm(self.head_dim), RMSNorm(self.head_dim)
def precompute_kv(self, enc_out: torch.Tensor):
B, S, _ = enc_out.shape
k, v = self.kv_proj(enc_out).chunk(2, dim=-1)
return (
self.k_norm(k.view(B, S, self.n_heads, self.head_dim).transpose(1, 2)),
v.view(B, S, self.n_heads, self.head_dim).transpose(1, 2),
)
def step_kv(self, x_step, k_cross, v_cross, enc_mask) -> torch.Tensor:
B, T, D = x_step.shape
q = self.q_norm(self.q_proj(x_step).view(B, T, self.n_heads, self.head_dim).transpose(1, 2))
y = F.scaled_dot_product_attention(q, k_cross, v_cross, attn_mask=enc_mask, is_causal=False)
return self.out(y.transpose(1, 2).reshape(B, T, D))
class EncoderLayer(nn.Module):
def __init__(self, d_model: int, n_heads: int, ffn_dim: int):
super().__init__()
self.norm1, self.self_attn = RMSNorm(d_model), SelfAttention(d_model, n_heads, is_causal=False)
self.norm2, self.mlp = RMSNorm(d_model), SwiGLU(d_model, ffn_dim)
def forward(self, x, rope, enc_mask):
x = x + self.self_attn(self.norm1(x), rope, enc_mask)
return x + self.mlp(self.norm2(x))
class DecoderLayer(nn.Module):
def __init__(self, d_model: int, n_heads: int, ffn_dim: int):
super().__init__()
self.norm1, self.self_attn = RMSNorm(d_model), SelfAttention(d_model, n_heads, is_causal=True)
self.norm2, self.cross_attn = RMSNorm(d_model), CrossAttention(d_model, n_heads)
self.norm3, self.mlp = RMSNorm(d_model), SwiGLU(d_model, ffn_dim)
def step_kv(self, x_step, cos_p, sin_p, pos, k_self, v_self, k_cross, v_cross, enc_mask):
x_step = x_step + self.self_attn.step_kv(self.norm1(x_step), cos_p, sin_p, pos, k_self, v_self)
x_step = x_step + self.cross_attn.step_kv(self.norm2(x_step), k_cross, v_cross, enc_mask)
return x_step + self.mlp(self.norm3(x_step))
class FastKVTranslator(nn.Module):
def __init__(
self,
vocab_size=65664,
d_model=768,
n_heads=12,
enc_layers=8,
dec_layers=8,
ffn_dim=2816,
max_seq_len=1024,
kv_alloc=16384,
):
super().__init__()
self.d_model, self.n_heads, self.head_dim, self.dec_layers = (
d_model,
n_heads,
d_model // n_heads,
dec_layers,
)
self.kv_alloc = kv_alloc
self.embed_scale = math.sqrt(d_model)
self.embed_tokens = nn.Embedding(vocab_size, d_model, padding_idx=PAD_ID)
self.rope = RotaryEmbedding(self.head_dim, max_seq_len=max_seq_len)
self.encoder = nn.ModuleList([EncoderLayer(d_model, n_heads, ffn_dim) for _ in range(enc_layers)])
self.enc_norm = RMSNorm(d_model)
self.decoder = nn.ModuleList([DecoderLayer(d_model, n_heads, ffn_dim) for _ in range(dec_layers)])
self.dec_norm = RMSNorm(d_model)
self.lm_head = nn.Linear(d_model, vocab_size, bias=False)
self._k_pool = self._v_pool = None
def _get_kv_caches(self, B: int, max_new_tokens: int, dtype: torch.dtype, dev: torch.device):
needed = self.dec_layers * B * self.n_heads * max_new_tokens * self.head_dim
if self._k_pool is None or self._k_pool.numel() < needed:
self._k_pool = self._v_pool = None
alloc = max(needed, self.dec_layers * self.kv_alloc * self.n_heads * self.head_dim)
self._k_pool = torch.empty(alloc, dtype=dtype, device=dev)
self._v_pool = torch.empty(alloc, dtype=dtype, device=dev)
shape = (self.dec_layers, B, self.n_heads, max_new_tokens, self.head_dim)
return self._k_pool[:needed].view(shape), self._v_pool[:needed].view(shape)
@torch.inference_mode()
def translate_batch_kv(
self,
token_id_lists: list,
direction: str = "my2en",
max_new_tokens: int = 192,
rep_penalty: float = 1.12,
) -> list:
B = len(token_id_lists)
if B == 0:
return []
dir_tok = TOK_2EN if direction == "my2en" else TOK_2MY
max_len = min(512, max(len(s) for s in token_id_lists) + 2)
min_len = min(512, min(len(s) for s in token_id_lists) + 2)
max_s = min(512, ((max_len + 7) // 8) * 8)
src_np = np.full((B, max_s), PAD_ID, dtype=np.int64)
for i, s in enumerate(token_id_lists):
trunc = s[:510]
L = len(trunc)
src_np[i, 0] = dir_tok
src_np[i, 1 : 1 + L] = trunc
src_np[i, 1 + L] = EOS_ID
src_ids = torch.from_numpy(src_np).to(DEVICE)
enc_mask = (src_ids != PAD_ID).unsqueeze(1).unsqueeze(2) if (min_len < max_s) else None
x_enc = self.embed_tokens(src_ids) * self.embed_scale
for layer in self.encoder:
x_enc = layer(x_enc, self.rope, enc_mask)
enc_out = self.enc_norm(x_enc)
cross_kv = [layer.cross_attn.precompute_kv(enc_out) for layer in self.decoder]
k_self_cache, v_self_cache = self._get_kv_caches(B, max_new_tokens, COMPUTE_DTYPE, DEVICE)
lm_w = self.lm_head.weight[:65536]
cos_all, sin_all = self.rope.cos_cached, self.rope.sin_cached
eos_tensor = torch.tensor(EOS_ID, dtype=torch.long, device=DEVICE)
active_orig_idx = torch.arange(B, dtype=torch.long, device=DEVICE)
active_done = torch.zeros(B, dtype=torch.bool, device=DEVICE)
active_gen = torch.empty((B, max_new_tokens), dtype=torch.long, device=DEVICE)
finished_gen = torch.full((B, max_new_tokens), EOS_ID, dtype=torch.long, device=DEVICE)
cur_tok = torch.full((B, 1), BOS_ID, dtype=torch.long, device=DEVICE)
actual_max_pos = max_new_tokens
for pos in range(max_new_tokens):
cos_p, sin_p = cos_all[:, :, pos : pos + 1, :], sin_all[:, :, pos : pos + 1, :]
x_dec = self.embed_tokens(cur_tok) * self.embed_scale
for l_idx, layer in enumerate(self.decoder):
kc, vc = cross_kv[l_idx]
x_dec = layer.step_kv(
x_dec, cos_p, sin_p, pos, k_self_cache[l_idx], v_self_cache[l_idx], kc, vc, enc_mask
)
logits = F.linear(self.dec_norm(x_dec)[:, 0, :], lm_w)
logits[:, :2] = -30000.0
logits[:, 3] = -30000.0
if rep_penalty != 1.0 and pos > 0:
prev_toks = active_gen[:, :pos]
s_logits = torch.gather(logits, 1, prev_toks)
s_logits = torch.where(s_logits > 0, s_logits / rep_penalty, s_logits * rep_penalty)
logits.scatter_(1, prev_toks, s_logits)
nxt = torch.where(active_done, eos_tensor, logits.argmax(dim=-1))
active_gen[:, pos] = nxt
active_done = active_done | (nxt == EOS_ID)
cur_tok = nxt.unsqueeze(1)
if (pos + 1) & 3 == 0:
keep_mask = ~active_done
n_keep = int(keep_mask.sum().item())
if n_keep == 0:
finished_gen[active_orig_idx, : pos + 1] = active_gen[:, : pos + 1]
actual_max_pos = pos + 1
break
cur_B = active_orig_idx.size(0)
if cur_B - n_keep >= 16 or n_keep * 10 <= cur_B * 8:
finished_gen[active_orig_idx[active_done], : pos + 1] = active_gen[active_done, : pos + 1]
keep_idx = torch.nonzero(keep_mask, as_tuple=False).squeeze(-1)
active_orig_idx = active_orig_idx[keep_idx]
active_done = active_done[keep_idx]
active_gen = active_gen[keep_idx]
cur_tok = cur_tok[keep_idx]
if enc_mask is not None:
enc_mask = enc_mask[keep_idx]
cross_kv = [(kc[keep_idx], vc[keep_idx]) for kc, vc in cross_kv]
k_self_cache = k_self_cache[:, keep_idx]
v_self_cache = v_self_cache[:, keep_idx]
else:
finished_gen[active_orig_idx, :actual_max_pos] = active_gen[:, :actual_max_pos]
gen_cpu = finished_gen[:, :actual_max_pos].cpu().tolist()
out_ids = []
for row in gen_cpu:
try:
out_ids.append(row[: row.index(EOS_ID)])
except ValueError:
out_ids.append(row)
return out_ids
sp = spm.SentencePieceProcessor()
sp.load(os.path.join(MODEL_DIR, "tokenizer.model"))
model = FastKVTranslator()
sd = load_file(os.path.join(MODEL_DIR, "model.safetensors"))
model.load_state_dict(sd, strict=False)
model.lm_head.weight = model.embed_tokens.weight
model = model.to(device=DEVICE, dtype=COMPUTE_DTYPE).eval()
# --- Usage Examples ---
WS_RE = re.compile(r"[ \t]+")
def normalize_myanmar(text: str) -> str:
return WS_RE.sub(
" ", text.replace("\u103a\u1037", "\u1037\u103a").replace("\u1036\u102f", "\u102f\u1036")
).strip()
def translate(texts: list[str], direction: str = "my2en") -> list[str]:
cleaned = [normalize_myanmar(t) if direction == "my2en" else t.strip() for t in texts]
toks = [sp.encode_as_ids(t) for t in cleaned]
max_src = min(510, max(len(t) for t in toks))
max_new = min(256, max(48, int(max_src * 1.4) + 16))
out_ids = model.translate_batch_kv(toks, direction=direction, max_new_tokens=max_new)
return [sp.decode_ids(ids).strip() for ids in out_ids]
# Burmese -> English
print(translate(["အီလက်ထရွန်းနစ် သည် လျှပ်စစ်ပတ်လမ်းများကို လေ့လာသည့် ပညာ ဖြစ်သည်။"], direction="my2en"))
# English -> Burmese
print(translate(["Electronics is the study of electrical circuits and how they interact."], direction="en2my"))
For large-scale corpus translation, this production runner adds:
seg_to_uid) so repeated headings, titles, or authors are translated only once per chunk.MAX_BATCH_SEGS=1024, MAX_BATCH_TOKENS=57344) sorted by token length to eliminate padding waste.split_burmese_v3) for arbitrarily long articles and books.NVIDIA GeForce RTX 5090, bfloat16)freococo/jw_myanmar_bible_dataset (31,078 verses): completed in a few seconds (5.71 MB Parquet).kalixlouiis/myanmar-literature-corpus (371,917 rows across 3 combined columns): ~49s per 50,000-row shard (8.2–8.3 GB peak VRAM).import os, socket
os.environ["PYTORCH_CUDA_ALLOC_CONF"] = "expandable_segments:True"
_orig_getaddrinfo = socket.getaddrinfo
def _ipv4_first(*args, **kwargs):
res = _orig_getaddrinfo(*args, **kwargs)
v4 = [r for r in res if r[0] == socket.AF_INET]
return v4 if v4 else res
socket.getaddrinfo = _ipv4_first
import re, gc, glob, time, math, shutil
from concurrent.futures import ThreadPoolExecutor
import numpy as np
import pyarrow as pa
import pyarrow.parquet as pq
import sentencepiece as spm
import torch
import torch.nn as nn
import torch.nn.functional as F
from safetensors.torch import load_file
from huggingface_hub import HfApi, snapshot_download, get_token
from datasets import load_dataset, concatenate_datasets
# ==============================================================================
# CONFIGURATION
# ==============================================================================
TARGET_PRIVATE_REPO = "your-username/myanmar-english-corpus"
SOURCE_REPO_ID = "kalixlouiis/myanmar-literature-corpus"
TEXT_COLUMNS = ["text", "author", "book_title"] # Joined with "\n" per row
HF_TOKEN = os.environ.get("HF_TOKEN") or get_token()
assert HF_TOKEN, "Not logged in! Run: huggingface-cli login (or set HF_TOKEN)"
BASE_DIR = "/workspace" if os.path.exists("/workspace") else os.path.expanduser("~")
MODEL_REPO = "freococo/MyanmarTranslator-210M-Pro"
MODEL_DIR = os.path.join(BASE_DIR, "MyanmarTranslator-210M-Pro")
OUT_DIR = os.path.join(BASE_DIR, "translated_parquets")
os.makedirs(OUT_DIR, exist_ok=True)
MAX_BATCH_SEGS, MAX_BATCH_TOKENS, KV_ALLOC = 1024, 57_344, 110_000
BIG_SHARD_ROWS, CUR_SUPER_CHUNK = 50_000, 50_000
DELETE_LOCAL_AFTER_UPLOAD = True
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
COMPUTE_DTYPE = torch.bfloat16 if (torch.cuda.is_available() and torch.cuda.get_device_capability()[0] >= 8) else torch.float16
if torch.cuda.is_available():
torch.backends.cuda.enable_flash_sdp(True)
torch.backends.cuda.enable_mem_efficient_sdp(True)
torch.backends.cuda.enable_math_sdp(True)
print(f"🖥️ GPU: {torch.cuda.get_device_name(0)} | Dtype: {COMPUTE_DTYPE} | Batch: {MAX_BATCH_SEGS}/{MAX_BATCH_TOKENS}")
def hf_retry(fn, *args, **kwargs):
for attempt in range(1, 7):
try:
return fn(*args, **kwargs)
except Exception as e:
print(f" ⚠️ HF retry {attempt}/6: {e}")
if attempt == 6: raise
time.sleep(5 * attempt)
api = HfApi(token=HF_TOKEN)
hf_retry(api.create_repo, repo_id=TARGET_PRIVATE_REPO, repo_type="dataset", private=True, exist_ok=True)
existing_remote_files = set(hf_retry(api.list_repo_files, repo_id=TARGET_PRIVATE_REPO, repo_type="dataset"))
VOCAB_SIZE, UNK_ID, BOS_ID, EOS_ID, PAD_ID = 65664, 0, 1, 2, 3
TOK_2MY, TOK_2EN = 65536, 65537
class RMSNorm(nn.Module):
def __init__(self, dim: int, eps: float = 1e-6):
super().__init__()
self.dim, self.eps = (dim,), eps
self.weight = nn.Parameter(torch.ones(dim))
def forward(self, x: torch.Tensor) -> torch.Tensor:
return F.rms_norm(x, self.dim, self.weight, self.eps)
class RotaryEmbedding(nn.Module):
def __init__(self, dim: int, max_seq_len: int = 1024, theta: float = 10000.0):
super().__init__()
inv_freq = 1.0 / (theta ** (torch.arange(0, dim, 2, dtype=torch.float32) / dim))
t = torch.arange(max_seq_len, dtype=torch.float32)
freqs = torch.outer(t, inv_freq)
self.register_buffer("cos_cached", freqs.cos()[None, None, :, :], persistent=False)
self.register_buffer("sin_cached", freqs.sin()[None, None, :, :], persistent=False)
def forward(self, x: torch.Tensor) -> torch.Tensor:
L = x.size(2)
cos, sin = self.cos_cached[:, :, :L, :], self.sin_cached[:, :, :L, :]
x1, x2 = x[..., ::2], x[..., 1::2]
return torch.cat((x1 * cos - x2 * sin, x1 * sin + x2 * cos), dim=-1)
class SwiGLU(nn.Module):
def __init__(self, d_model: int, ffn_dim: int):
super().__init__()
self.gate_up = nn.Linear(d_model, 2 * ffn_dim, bias=False)
self.down = nn.Linear(ffn_dim, d_model, bias=False)
def forward(self, x: torch.Tensor) -> torch.Tensor:
gate, up = self.gate_up(x).chunk(2, dim=-1)
return self.down(F.silu(gate) * up)
class SelfAttention(nn.Module):
def __init__(self, d_model: int, n_heads: int, is_causal: bool = False):
super().__init__()
self.n_heads, self.head_dim, self.is_causal = n_heads, d_model // n_heads, is_causal
self.qkv = nn.Linear(d_model, 3 * d_model, bias=False)
self.out = nn.Linear(d_model, d_model, bias=False)
self.q_norm, self.k_norm = RMSNorm(self.head_dim), RMSNorm(self.head_dim)
def forward(self, x: torch.Tensor, rope: RotaryEmbedding, attn_mask: torch.Tensor = None) -> torch.Tensor:
B, L, D = x.shape
q, k, v = self.qkv(x).chunk(3, dim=-1)
q = self.q_norm(q.view(B, L, self.n_heads, self.head_dim).transpose(1, 2))
k = self.k_norm(k.view(B, L, self.n_heads, self.head_dim).transpose(1, 2))
v = v.view(B, L, self.n_heads, self.head_dim).transpose(1, 2)
q, k = rope(q), rope(k)
y = F.scaled_dot_product_attention(q, k, v, attn_mask=None if self.is_causal else attn_mask, is_causal=self.is_causal)
return self.out(y.transpose(1, 2).reshape(B, L, D))
def step_kv(self, x_step, cos_p, sin_p, pos, k_cache, v_cache) -> torch.Tensor:
B, _, D = x_step.shape
q, k, v = self.qkv(x_step).chunk(3, dim=-1)
q = self.q_norm(q.view(B, 1, self.n_heads, self.head_dim).transpose(1, 2))
k = self.k_norm(k.view(B, 1, self.n_heads, self.head_dim).transpose(1, 2))
v = v.view(B, 1, self.n_heads, self.head_dim).transpose(1, 2)
q1, q2 = q[..., ::2], q[..., 1::2]
k1, k2 = k[..., ::2], k[..., 1::2]
q = torch.cat((q1 * cos_p - q2 * sin_p, q1 * sin_p + q2 * cos_p), dim=-1)
k = torch.cat((k1 * cos_p - k2 * sin_p, k1 * sin_p + k2 * cos_p), dim=-1)
k_cache[:, :, pos : pos + 1, :] = k
v_cache[:, :, pos : pos + 1, :] = v
y = F.scaled_dot_product_attention(q, k_cache[:, :, : pos + 1, :], v_cache[:, :, : pos + 1, :], is_causal=False)
return self.out(y.transpose(1, 2).reshape(B, 1, D))
class CrossAttention(nn.Module):
def __init__(self, d_model: int, n_heads: int):
super().__init__()
self.n_heads, self.head_dim = n_heads, d_model // n_heads
self.q_proj = nn.Linear(d_model, d_model, bias=False)
self.kv_proj = nn.Linear(d_model, 2 * d_model, bias=False)
self.out = nn.Linear(d_model, d_model, bias=False)
self.q_norm, self.k_norm = RMSNorm(self.head_dim), RMSNorm(self.head_dim)
def precompute_kv(self, enc_out: torch.Tensor):
B, S, _ = enc_out.shape
k, v = self.kv_proj(enc_out).chunk(2, dim=-1)
return self.k_norm(k.view(B, S, self.n_heads, self.head_dim).transpose(1, 2)), v.view(B, S, self.n_heads, self.head_dim).transpose(1, 2)
def step_kv(self, x_step, k_cross, v_cross, enc_mask) -> torch.Tensor:
B, T, D = x_step.shape
q = self.q_norm(self.q_proj(x_step).view(B, T, self.n_heads, self.head_dim).transpose(1, 2))
y = F.scaled_dot_product_attention(q, k_cross, v_cross, attn_mask=enc_mask, is_causal=False)
return self.out(y.transpose(1, 2).reshape(B, T, D))
class EncoderLayer(nn.Module):
def __init__(self, d_model: int, n_heads: int, ffn_dim: int):
super().__init__()
self.norm1, self.self_attn = RMSNorm(d_model), SelfAttention(d_model, n_heads, is_causal=False)
self.norm2, self.mlp = RMSNorm(d_model), SwiGLU(d_model, ffn_dim)
def forward(self, x, rope, enc_mask):
x = x + self.self_attn(self.norm1(x), rope, enc_mask)
return x + self.mlp(self.norm2(x))
class DecoderLayer(nn.Module):
def __init__(self, d_model: int, n_heads: int, ffn_dim: int):
super().__init__()
self.norm1, self.self_attn = RMSNorm(d_model), SelfAttention(d_model, n_heads, is_causal=True)
self.norm2, self.cross_attn = RMSNorm(d_model), CrossAttention(d_model, n_heads)
self.norm3, self.mlp = RMSNorm(d_model), SwiGLU(d_model, ffn_dim)
def step_kv(self, x_step, cos_p, sin_p, pos, k_self, v_self, k_cross, v_cross, enc_mask):
x_step = x_step + self.self_attn.step_kv(self.norm1(x_step), cos_p, sin_p, pos, k_self, v_self)
x_step = x_step + self.cross_attn.step_kv(self.norm2(x_step), k_cross, v_cross, enc_mask)
return x_step + self.mlp(self.norm3(x_step))
class FastKVTranslator(nn.Module):
def __init__(self, vocab_size=65664, d_model=768, n_heads=12, enc_layers=8, dec_layers=8, ffn_dim=2816, max_seq_len=1024):
super().__init__()
self.d_model, self.n_heads, self.head_dim, self.dec_layers = d_model, n_heads, d_model // n_heads, dec_layers
self.embed_scale = math.sqrt(d_model)
self.embed_tokens = nn.Embedding(vocab_size, d_model, padding_idx=PAD_ID)
self.rope = RotaryEmbedding(self.head_dim, max_seq_len=max_seq_len)
self.encoder = nn.ModuleList([EncoderLayer(d_model, n_heads, ffn_dim) for _ in range(enc_layers)])
self.enc_norm = RMSNorm(d_model)
self.decoder = nn.ModuleList([DecoderLayer(d_model, n_heads, ffn_dim) for _ in range(dec_layers)])
self.dec_norm = RMSNorm(d_model)
self.lm_head = nn.Linear(d_model, vocab_size, bias=False)
self._k_pool = self._v_pool = None
def _get_kv_caches(self, B: int, max_new_tokens: int, dtype: torch.dtype, dev: torch.device):
needed = self.dec_layers * B * self.n_heads * max_new_tokens * self.head_dim
if self._k_pool is None or self._k_pool.numel() < needed:
if self._k_pool is not None:
del self._k_pool, self._v_pool
self._k_pool = self._v_pool = None
torch.cuda.empty_cache()
alloc = max(needed, self.dec_layers * KV_ALLOC * self.n_heads * self.head_dim)
self._k_pool = torch.empty(alloc, dtype=dtype, device=dev)
self._v_pool = torch.empty(alloc, dtype=dtype, device=dev)
shape = (self.dec_layers, B, self.n_heads, max_new_tokens, self.head_dim)
return self._k_pool[:needed].view(shape), self._v_pool[:needed].view(shape)
@torch.inference_mode()
def translate_batch_kv(self, token_id_lists: list, direction: str = "my2en", max_new_tokens: int = 192, rep_penalty: float = 1.12) -> list:
B = len(token_id_lists)
if B == 0: return []
dir_tok = TOK_2EN if direction == "my2en" else TOK_2MY
max_len = min(512, max(len(s) for s in token_id_lists) + 2)
min_len = min(512, min(len(s) for s in token_id_lists) + 2)
max_s = min(512, ((max_len + 7) // 8) * 8)
src_np = np.full((B, max_s), PAD_ID, dtype=np.int64)
for i, s in enumerate(token_id_lists):
trunc = s[:510]
L = len(trunc)
src_np[i, 0] = dir_tok
src_np[i, 1 : 1 + L] = trunc
src_np[i, 1 + L] = EOS_ID
src_ids = torch.from_numpy(src_np).to(device)
enc_mask = (src_ids != PAD_ID).unsqueeze(1).unsqueeze(2) if (min_len < max_s) else None
x_enc = self.embed_tokens(src_ids) * self.embed_scale
for layer in self.encoder:
x_enc = layer(x_enc, self.rope, enc_mask)
enc_out = self.enc_norm(x_enc)
cross_kv = [layer.cross_attn.precompute_kv(enc_out) for layer in self.decoder]
k_self_cache, v_self_cache = self._get_kv_caches(B, max_new_tokens, COMPUTE_DTYPE, device)
lm_w = self.lm_head.weight[:65536]
cos_all, sin_all = self.rope.cos_cached, self.rope.sin_cached
eos_tensor = torch.tensor(EOS_ID, dtype=torch.long, device=device)
active_orig_idx = torch.arange(B, dtype=torch.long, device=device)
active_done = torch.zeros(B, dtype=torch.bool, device=device)
active_gen = torch.empty((B, max_new_tokens), dtype=torch.long, device=device)
finished_gen = torch.full((B, max_new_tokens), EOS_ID, dtype=torch.long, device=device)
cur_tok = torch.full((B, 1), BOS_ID, dtype=torch.long, device=device)
actual_max_pos = max_new_tokens
for pos in range(max_new_tokens):
cos_p, sin_p = cos_all[:, :, pos : pos + 1, :], sin_all[:, :, pos : pos + 1, :]
x_dec = self.embed_tokens(cur_tok) * self.embed_scale
for l_idx, layer in enumerate(self.decoder):
kc, vc = cross_kv[l_idx]
x_dec = layer.step_kv(x_dec, cos_p, sin_p, pos, k_self_cache[l_idx], v_self_cache[l_idx], kc, vc, enc_mask)
logits = F.linear(self.dec_norm(x_dec)[:, 0, :], lm_w)
logits[:, :2] = -30000.0
logits[:, 3] = -30000.0
if rep_penalty != 1.0 and pos > 0:
prev_toks = active_gen[:, :pos]
s_logits = torch.gather(logits, 1, prev_toks)
s_logits = torch.where(s_logits > 0, s_logits / rep_penalty, s_logits * rep_penalty)
logits.scatter_(1, prev_toks, s_logits)
nxt = torch.where(active_done, eos_tensor, logits.argmax(dim=-1))
active_gen[:, pos] = nxt
active_done = active_done | (nxt == EOS_ID)
cur_tok = nxt.unsqueeze(1)
if (pos + 1) & 3 == 0:
keep_mask = ~active_done
n_keep = int(keep_mask.sum().item())
if n_keep == 0:
finished_gen[active_orig_idx, : pos + 1] = active_gen[:, : pos + 1]
actual_max_pos = pos + 1
break
cur_B = active_orig_idx.size(0)
if cur_B - n_keep >= 16 or n_keep * 10 <= cur_B * 8:
finished_gen[active_orig_idx[active_done], : pos + 1] = active_gen[active_done, : pos + 1]
keep_idx = torch.nonzero(keep_mask, as_tuple=False).squeeze(-1)
active_orig_idx = active_orig_idx[keep_idx]
active_done = active_done[keep_idx]
active_gen = active_gen[keep_idx]
cur_tok = cur_tok[keep_idx]
if enc_mask is not None: enc_mask = enc_mask[keep_idx]
cross_kv = [(kc[keep_idx], vc[keep_idx]) for kc, vc in cross_kv]
k_self_cache = k_self_cache[:, keep_idx]
v_self_cache = v_self_cache[:, keep_idx]
else:
finished_gen[active_orig_idx, :actual_max_pos] = active_gen[:, :actual_max_pos]
gen_cpu = finished_gen[:, :actual_max_pos].cpu().tolist()
out_ids = []
for row in gen_cpu:
try: out_ids.append(row[: row.index(EOS_ID)])
except ValueError: out_ids.append(row)
return out_ids
if not os.path.exists(os.path.join(MODEL_DIR, "model.safetensors")):
hf_retry(snapshot_download, repo_id=MODEL_REPO, local_dir=MODEL_DIR, ignore_patterns=["checkpoint-*/*", "*.pt", "*.txt"], token=HF_TOKEN)
sp = spm.SentencePieceProcessor()
sp.load(os.path.join(MODEL_DIR, "tokenizer.model"))
model = FastKVTranslator()
sd = load_file(os.path.join(MODEL_DIR, "model.safetensors"))
model.load_state_dict(sd, strict=False)
model.lm_head.weight = model.embed_tokens.weight
model = model.to(device=device, dtype=COMPUTE_DTYPE).eval()
del sd; gc.collect(); torch.cuda.empty_cache()
MYANMAR_CHAR_RE = re.compile(r"[\u1000-\u109F]")
WS_RE, PARA_SPLIT_RE, SENT_SPLIT_RE, CLAUSE_SPLIT_RE = re.compile(r"[ \t]+"), re.compile(r"။\s*။|\n+"), re.compile(r"(?<=။)"), re.compile(r"(?<=၊)")
N_CPU_THREADS = min(6, os.cpu_count() or 4)
PARQUET_SCHEMA = pa.schema([("myanmar_text_original", pa.string()), ("english_text_translation", pa.string())])
def normalize_myanmar_unicode(text: str) -> str:
return WS_RE.sub(" ", text.replace("\u103a\u1037", "\u1037\u103a").replace("\u1036\u102f", "\u102f\u1036")).strip()
def _hard_split(text: str, max_chars: int) -> list:
if len(text) <= max_chars: return [text]
words = text.split(" ")
if len(words) > 1:
out, cur = [], ""
for w in words:
if not cur: cur = w if len(w) <= max_chars else w[:max_chars]
elif len(cur) + len(w) + 1 <= max_chars: cur = cur + " " + w
else: out.append(cur); cur = w
if cur: out.append(cur)
if all(len(x) <= max_chars for x in out): return out
return [text[i : i + max_chars] for i in range(0, len(text), max_chars)]
def split_burmese_v3(text: str, target_chars: int = 240, max_chars: int = 320) -> list:
para_chunks = []
for para in (p.strip() for p in PARA_SPLIT_RE.split(text) if p.strip()):
raw_sents = [s.strip() for s in SENT_SPLIT_RE.split(para) if s.strip()]
merged_sents, i, n = [], 0, len(raw_sents)
while i < n:
if len(raw_sents[i]) < 42 and i + 1 < n:
raw_sents[i + 1] = raw_sents[i] + " " + raw_sents[i + 1]
i += 1; continue
merged_sents.append(raw_sents[i]); i += 1
pieces = []
for s in merged_sents:
if len(s) <= max_chars: pieces.append(s)
else:
sub = ""
for cl in (c.strip() for c in CLAUSE_SPLIT_RE.split(s) if c.strip()):
if not sub: sub = cl
elif len(sub) + len(cl) + 1 <= target_chars or len(cl) < 18: sub = sub + " " + cl
else: pieces.extend(_hard_split(sub, max_chars)); sub = cl
if sub: pieces.extend(_hard_split(sub, max_chars))
chunks, cur = [], ""
for p in pieces:
if not cur: cur = p
elif len(cur) + len(p) + 1 <= target_chars: cur = cur + " " + p
else: chunks.append(cur); cur = p
if cur: chunks.append(cur)
if chunks: para_chunks.append(chunks)
return para_chunks
def sp_encode_batch(texts: list) -> list:
try: return sp.encode(texts, out_type=int, num_threads=N_CPU_THREADS)
except TypeError: return [sp.encode_as_ids(t) for t in texts]
def sp_decode_batch(id_lists: list) -> list:
try: return [s.strip() for s in sp.decode(id_lists)]
except Exception: return [sp.decode_ids(ids).strip() for ids in id_lists]
def find_uncovered_gaps(short_name: str, total_src_rows: int, remote_files: set):
part_re = re.compile(rf"^data/{re.escape(short_name)}/part-(\d+)-(\d+)\.parquet$")
covered = []
for fn in remote_files:
m_p = part_re.match(fn)
if m_p: covered.append((int(m_p.group(1)), int(m_p.group(2))))
covered.sort()
merged = []
for s, e in covered:
s, e = max(0, s), min(total_src_rows, e)
if s >= e: continue
if merged and s <= merged[-1][1]: merged[-1] = (merged[-1][0], max(merged[-1][1], e))
else: merged.append((s, e))
gaps, cur = [], 0
for s, e in merged:
if cur < s: gaps.append((cur, s))
cur = max(cur, e)
if cur < total_src_rows: gaps.append((cur, total_src_rows))
return gaps, sum(e - s for s, e in merged)
def upload_parquet_worker(local_path: str, remote_path: str, repo_id_src: str):
for attempt in range(1, 7):
try:
t_up = time.time()
api.upload_file(
path_or_fileobj=local_path,
path_in_repo=remote_path,
repo_id=TARGET_PRIVATE_REPO,
repo_type="dataset",
commit_message=f"Add {remote_path} from {repo_id_src}",
)
print(f" ☁️ Uploaded {remote_path} in {time.time()-t_up:.1f}s!")
if DELETE_LOCAL_AFTER_UPLOAD and os.path.exists(local_path):
os.remove(local_path)
return
except Exception as e:
print(f" ⚠️ Upload retry {attempt}/6 for {remote_path} ({e})...")
if attempt == 6: raise
time.sleep(5 * attempt)
short_name = SOURCE_REPO_ID.split("/")[-1]
ds_dict = hf_retry(load_dataset, SOURCE_REPO_ID, token=HF_TOKEN)
cur_ds = concatenate_datasets([ds_dict[k] for k in ds_dict.keys()]) if hasattr(ds_dict, "keys") else ds_dict
total_src_rows = len(cur_ds)
for c in TEXT_COLUMNS:
assert c in cur_ds.column_names, f"'{c}' not found! Columns: {cur_ds.column_names}"
gaps, covered_rows = find_uncovered_gaps(short_name, total_src_rows, existing_remote_files)
if not gaps:
print(f"✅ All {total_src_rows:,} rows already uploaded!")
else:
shard_ranges = [(s, min(s + BIG_SHARD_ROWS, g_end)) for g_start, g_end in gaps for s in range(g_start, g_end, BIG_SHARD_ROWS)]
upload_executor = ThreadPoolExecutor(max_workers=1)
pending_uploads = []
for sh_idx, (sh_start, sh_end) in enumerate(shard_ranges, 1):
remote_path = f"data/{short_name}/part-{sh_start:09d}-{sh_end:09d}.parquet"
local_path = os.path.join(OUT_DIR, f"{short_name}_part-{sh_start:09d}-{sh_end:09d}.parquet")
if remote_path in existing_remote_files: continue
t_sh = time.time()
writer = pq.ParquetWriter(local_path, PARQUET_SCHEMA, compression="snappy", use_dictionary=True)
shard_out_rows = 0
for sc_start in range(sh_start, sh_end, CUR_SUPER_CHUNK):
sc_end = min(sc_start + CUR_SUPER_CHUNK, sh_end)
sub_ds = cur_ds.select(range(sc_start, sc_end))
cols_data = {c: sub_ds[c] for c in TEXT_COLUMNS}
doc_originals, doc_para_lens, all_segments = [], [], []
for r in range(sc_end - sc_start):
parts = [cols_data[c][r].strip() for c in TEXT_COLUMNS if isinstance(cols_data[c][r], str) and cols_data[c][r].strip()]
if not parts: continue
raw_val = "\n".join(parts)
if not MYANMAR_CHAR_RE.search(raw_val): continue
norm_val = normalize_myanmar_unicode(raw_val)
if not norm_val: continue
p_chunks = split_burmese_v3(norm_val)
if not p_chunks: continue
doc_originals.append(norm_val)
doc_para_lens.append([len(p) for p in p_chunks])
for p in p_chunks: all_segments.extend(p)
del sub_ds, cols_data
if not all_segments: continue
seg_to_uid, unique_segs = {}, []
seg_uids = np.empty(len(all_segments), dtype=np.int32)
for idx, s in enumerate(all_segments):
uid = seg_to_uid.get(s)
if uid is None:
uid = len(unique_segs); seg_to_uid[s] = uid; unique_segs.append(s)
seg_uids[idx] = uid
del seg_to_uid, all_segments
tokenized_unique = sp_encode_batch(unique_segs)
del unique_segs
lengths = np.array([len(t) for t in tokenized_unique], dtype=np.int32)
sorted_order = np.argsort(lengths)
translated_unique = [""] * len(tokenized_unique)
dyn_batches, cur_b, cur_max_l = [], [], 0
for uid in sorted_order:
l = min(512, int(lengths[uid]))
new_max = max(cur_max_l, l)
if cur_b and (len(cur_b) >= MAX_BATCH_SEGS or (len(cur_b) + 1) * new_max > MAX_BATCH_TOKENS):
dyn_batches.append(cur_b); cur_b, cur_max_l = [int(uid)], l
else:
cur_b.append(int(uid)); cur_max_l = new_max
if cur_b: dyn_batches.append(cur_b)
for batch_uids in dyn_batches:
batch_toks = [tokenized_unique[u] for u in batch_uids]
max_src_in_b = min(510, max(len(t) for t in batch_toks))
dyn_max_new = min(208, max(40, int(max_src_in_b * 1.35) + 12))
out_id_lists = model.translate_batch_kv(batch_toks, direction="my2en", max_new_tokens=dyn_max_new)
for u, dec in zip(batch_uids, sp_decode_batch(out_id_lists)):
translated_unique[u] = dec
out_en_list, cursor = [], 0
for p_lens in doc_para_lens:
paras_en = []
for plen in p_lens:
paras_en.append(" ".join(translated_unique[seg_uids[cursor + k]] for k in range(plen)))
cursor += plen
out_en_list.append("\n\n".join(paras_en).strip())
writer.write_table(pa.Table.from_pydict({
"myanmar_text_original": doc_originals,
"english_text_translation": out_en_list,
}, schema=PARQUET_SCHEMA))
shard_out_rows += len(doc_originals)
del doc_originals, doc_para_lens, out_en_list, seg_uids, translated_unique, tokenized_unique, lengths, sorted_order, dyn_batches
torch.cuda.empty_cache()
writer.close()
gc.collect()
if shard_out_rows > 0:
pending_uploads.append(upload_executor.submit(upload_parquet_worker, local_path, remote_path, SOURCE_REPO_ID))
else:
os.remove(local_path)
for fut in pending_uploads:
fut.result()
upload_executor.shutdown(wait=True)
print(f"🎉 DONE {SOURCE_REPO_ID} -> https://huggingface.co/datasets/{TARGET_PRIVATE_REPO}")
checkpoint-step-25000/training_state.pt 844 MBcheckpoint-step-25000/model.safetensors 844 MBmodel.safetensors 422 MB