From ac7c573f69a82d9b5fe23a91a767601ecf5ab41c Mon Sep 17 00:00:00 2001 From: Lukas Scheucher Date: Sat, 6 Jun 2026 20:06:38 +0200 Subject: [PATCH] feat(contextual): config, frozen-encoder wrapper, and throughput benchmark First slice of the contextual word-drift pipeline (issue #34): upgrade from static Word2Vec/TWEC drift to *contextual* drift by running the historical corpus through a frozen transformer encoder. - config.py: CONTEXTUAL_* knobs (model, layer, pooling, window/batch sizes, min-count, centering, PCA-removal, stopwords, output dirs). Append-only; nothing existing is touched. - pipeline/contextual_model.py: ContextualEncoder wraps a frozen bert-base-uncased (bf16, SDPA, inference_mode) with its fast tokenizer. encode_windows() returns hidden states + attention mask + a word_ids tensor that maps every subword back to its source word (word_ids(), not "##"). Hidden width read from config.hidden_size (never hardcode 768). - scripts/contextual_benchmark.py: throughput probe over real 2018 windows (writes nothing). Sweeps batch size, prints words/sec and an hours-per-year ETA table. - pyproject: declare transformers (was installed but undeclared). Benchmark result on the GB10: batch=128 is the optimum at ~80k words/s (dynamic padding makes smaller batches more efficient; far from memory-bound at 1.26 GB). Full 12B-token run ETA ~1.7 days. CONTEXTUAL_BATCH_SIZE set to 128. Co-Authored-By: Claude Opus 4.8 (1M context) --- config.py | 37 +++++++++ pipeline/contextual_model.py | 100 ++++++++++++++++++++++ pyproject.toml | 1 + scripts/contextual_benchmark.py | 125 ++++++++++++++++++++++++++++ uv.lock | 142 ++++++++++++++++++++++++++++++++ 5 files changed, 405 insertions(+) create mode 100644 pipeline/contextual_model.py create mode 100644 scripts/contextual_benchmark.py diff --git a/config.py b/config.py index 477c531d8..9b1fbcb95 100644 --- a/config.py +++ b/config.py @@ -28,3 +28,40 @@ ALIGNED_DIR = MODELS_DIR / "aligned" DRIFT_DIR = MODELS_DIR / "drift" TENSORBOARD_DIR = Path("runs") + +# --- Contextual drift pipeline --- +# Upgrade from static Word2Vec/TWEC drift to *contextual* drift: run the +# historical corpus through a frozen transformer encoder and aggregate per-word +# contextual centroids per year. A frozen shared encoder puts every year in one +# coordinate system, so no Procrustes/TWEC compass is needed. +CONTEXTUAL_MODEL = "bert-base-uncased" # fast WordPiece tokenizer, lowercase, SDPA +CONTEXTUAL_LAYER = -1 # which hidden state to pool (-1 = last_hidden_state) +CONTEXTUAL_POOLING = "first" # "first" subword | "mean" over subwords (mean deferred) +CONTEXTUAL_MAX_LEN = 128 # non-overlapping window length (words, pre-tokenization) +CONTEXTUAL_BATCH_SIZE = 128 # windows per forward; benchmark optimum on GB10 (~80k words/s) +CONTEXTUAL_TARGET_TOKENS_PER_YEAR = TARGET_TOKENS_PER_YEAR # 1B (full coverage) +CONTEXTUAL_MIN_COUNT = 50 # min observations for a trusted (word, year) centroid +CONTEXTUAL_CENTERING = True # per-year mean-centering (BERT anisotropy fix) +CONTEXTUAL_PCA_REMOVE_K = 0 # all-but-top-k PCA component removal; 0 = off +CONTEXTUAL_USE_STOPWORDS = True # skip function words when accumulating +CONTEXTUAL_DIR = MODELS_DIR / "contextual" +CONTEXTUAL_STATE_DIR = DATA_DIR / "contextual_state" + +# Small English function-word list. These are extremely high frequency, carry +# little drift signal, and would dominate the accumulator; we skip them when +# building the target-id tensor (gated by CONTEXTUAL_USE_STOPWORDS). +CONTEXTUAL_STOPWORDS = frozenset({ + "a", "an", "the", "and", "or", "but", "if", "then", "else", "when", + "of", "to", "in", "on", "at", "by", "for", "with", "about", "into", + "from", "up", "down", "out", "off", "over", "under", "as", "is", "am", + "are", "was", "were", "be", "been", "being", "have", "has", "had", + "do", "does", "did", "doing", "will", "would", "shall", "should", + "can", "could", "may", "might", "must", "not", "no", "nor", "so", + "than", "too", "very", "just", "this", "that", "these", "those", + "i", "you", "he", "she", "it", "we", "they", "me", "him", "her", + "us", "them", "my", "your", "his", "its", "our", "their", "mine", + "yours", "hers", "ours", "theirs", "who", "whom", "whose", "which", + "what", "where", "why", "how", "all", "any", "both", "each", "few", + "more", "most", "other", "some", "such", "only", "own", "same", + "here", "there", "again", "once", "also", "now", "ever", "never", +}) diff --git a/pipeline/contextual_model.py b/pipeline/contextual_model.py new file mode 100644 index 000000000..36228c483 --- /dev/null +++ b/pipeline/contextual_model.py @@ -0,0 +1,100 @@ +"""Frozen transformer encoder for the contextual-drift pipeline. + +Loads a frozen `bert-base-uncased` (or any `AutoModel`) with its *fast* +tokenizer and exposes `encode_windows`, which runs a bf16 `inference_mode` +forward over a batch of pre-tokenized word windows and returns the chosen +hidden-state layer together with the attention mask and a `word_ids` tensor +that maps every subword position back to its source word index. + +Why a frozen encoder: it puts every year in one coordinate system directly, so +no Procrustes/TWEC alignment is needed downstream. Why the fast tokenizer's +`word_ids()`: it maps subwords -> words correctly for WordPiece/BPE/SP, unlike +the brittle `"##"`-stripping heuristic. + +The hidden width is read from `model.config.hidden_size` -- never hardcode 768. +""" +from __future__ import annotations + +import torch +from transformers import AutoModel, AutoTokenizer + +from config import CONTEXTUAL_LAYER, CONTEXTUAL_MODEL + + +class ContextualEncoder: + def __init__( + self, + model_name: str = CONTEXTUAL_MODEL, + device: str = "cuda", + layer: int = CONTEXTUAL_LAYER, + dtype: torch.dtype = torch.bfloat16, + ) -> None: + self.model_name = model_name + self.device = device + self.layer = layer + + self.tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True) + if not self.tokenizer.is_fast: + raise RuntimeError( + f"{model_name} has no fast tokenizer; word_ids() alignment requires one." + ) + + self.model = AutoModel.from_pretrained( + model_name, + dtype=dtype, + attn_implementation="sdpa", + ) + self.model.eval().requires_grad_(False).to(device) + + self.hidden_dim: int = self.model.config.hidden_size + # Truncate to the model's positional limit; 128-word windows rarely exceed it. + self.max_subwords: int = min( + getattr(self.model.config, "max_position_embeddings", 512), 512 + ) + + @torch.inference_mode() + def encode_windows( + self, windows: list[list[str]] + ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor]: + """Encode a batch of word windows. + + Args: + windows: list of windows, each a list of lowercase word strings. + + Returns: + hidden: [B, L, H] hidden states of the configured layer (model dtype). + attn_mask: [B, L] attention mask (1 = real token). + word_ids: [B, L] long tensor; entry j is the source word index of + subword j, or -1 for special/padding tokens. On `device`. + """ + enc = self.tokenizer( + windows, + is_split_into_words=True, + padding=True, + truncation=True, + max_length=self.max_subwords, + return_tensors="pt", + ) + + # word_ids must be read from the BatchEncoding before moving tensors. + word_id_rows = [ + [-1 if w is None else w for w in enc.word_ids(i)] + for i in range(len(windows)) + ] + word_ids = torch.tensor(word_id_rows, dtype=torch.long, device=self.device) + + input_ids = enc["input_ids"].to(self.device) + attn_mask = enc["attention_mask"].to(self.device) + token_type = enc.get("token_type_ids") + kwargs = {"input_ids": input_ids, "attention_mask": attn_mask} + if token_type is not None: + kwargs["token_type_ids"] = token_type.to(self.device) + + if self.layer == -1: + out = self.model(**kwargs) + hidden = out.last_hidden_state + else: + out = self.model(**kwargs, output_hidden_states=True) + hidden = out.hidden_states[self.layer] + + return hidden, attn_mask, word_ids diff --git a/pyproject.toml b/pyproject.toml index f34a5f27a..671839382 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -16,5 +16,6 @@ dependencies = [ "tensorboard>=2.20.0", "torch>=2.12.0", "tqdm>=4.67.3", + "transformers>=5.10.0", "umap-learn>=0.5.12", ] diff --git a/scripts/contextual_benchmark.py b/scripts/contextual_benchmark.py new file mode 100644 index 000000000..c39b5596a --- /dev/null +++ b/scripts/contextual_benchmark.py @@ -0,0 +1,125 @@ +"""Throughput probe for the contextual-drift pipeline. RUN THIS FIRST. + +Pulls a few thousand real word-windows from one 2018 FineWeb snapshot (writes +nothing to disk), warms up the GPU, then sweeps the forward-pass batch size and +prints windows/sec, words/sec, subwords/sec and peak GPU memory, plus an +hours-per-year and total-wall-clock table for the full 12 B-token run. Use the +result to set CONTEXTUAL_BATCH_SIZE in config.py and confirm the ETA before +launching the real run. + + uv run python scripts/contextual_benchmark.py + uv run python scripts/contextual_benchmark.py --snapshot CC-MAIN-2018-30 --windows 3000 +""" +import argparse +import sys +import time +from pathlib import Path + +import torch + +sys.path.insert(0, str(Path(__file__).resolve().parent.parent)) + +from config import ( + CONTEXTUAL_MAX_LEN, + CONTEXTUAL_TARGET_TOKENS_PER_YEAR, + LANGUAGE_SCORE_THRESHOLD, + YEARS, +) +from pipeline.contextual_model import ContextualEncoder +from pipeline.snapshot_registry import get_snapshots + + +def collect_windows(snapshot: str, n_windows: int, max_len: int) -> list[list[str]]: + """Stream a snapshot and slice raw text into non-overlapping word windows. + + Mirrors the windowing the real pipeline uses (lowercase + whitespace split, + fixed-length non-overlapping windows); kept inline so the probe has no + dependency on the not-yet-built streaming module. + """ + from datasets import load_dataset + + ds = load_dataset("HuggingFaceFW/fineweb", name=snapshot, streaming=True, split="train") + ds = ds.filter(lambda x: x["language_score"] >= LANGUAGE_SCORE_THRESHOLD) + + windows: list[list[str]] = [] + for row in ds: + words = row["text"].lower().split() + for i in range(0, len(words), max_len): + win = words[i : i + max_len] + if win: + windows.append(win) + if len(windows) >= n_windows: + return windows + return windows + + +def main() -> None: + ap = argparse.ArgumentParser() + ap.add_argument("--device", default="cuda") + ap.add_argument("--snapshot", default=None, help="default: a 2018 snapshot") + ap.add_argument("--windows", type=int, default=2000) + ap.add_argument("--batch-sizes", type=int, nargs="+", default=[128, 256, 512]) + a = ap.parse_args() + + snapshot = a.snapshot or get_snapshots(2018)[6] # CC-MAIN-2018-30, mid-year + print(f"Loading encoder on {a.device}...", flush=True) + enc = ContextualEncoder(device=a.device) + print(f" model={enc.model_name} hidden_dim={enc.hidden_dim} max_subwords={enc.max_subwords}", flush=True) + + print(f"Pulling {a.windows} windows from {snapshot} (max_len={CONTEXTUAL_MAX_LEN})...", flush=True) + t0 = time.time() + windows = collect_windows(snapshot, a.windows, CONTEXTUAL_MAX_LEN) + avg_words = sum(len(w) for w in windows) / max(1, len(windows)) + print(f" got {len(windows)} windows, avg {avg_words:.1f} words/window ({time.time()-t0:.0f}s)", flush=True) + + # Warm up (kernels, autotune, allocator). + print("Warming up...", flush=True) + for _ in range(3): + enc.encode_windows(windows[:a.batch_sizes[0]]) + torch.cuda.synchronize() + + print(f"\n{'batch':>6} {'win/s':>9} {'words/s':>11} {'subwd/s':>11} {'peakGB':>8}", flush=True) + print("-" * 50, flush=True) + + results = [] + for bs in a.batch_sizes: + torch.cuda.reset_peak_memory_stats() + torch.cuda.synchronize() + t0 = time.time() + total_windows = 0 + total_subwords = 0 + for i in range(0, len(windows), bs): + batch = windows[i : i + bs] + _, attn_mask, _ = enc.encode_windows(batch) + total_windows += len(batch) + total_subwords += int(attn_mask.sum().item()) + torch.cuda.synchronize() + dt = time.time() - t0 + win_s = total_windows / dt + words_s = win_s * avg_words + subwd_s = total_subwords / dt + peak_gb = torch.cuda.max_memory_allocated() / 1e9 + results.append((bs, words_s)) + print(f"{bs:>6} {win_s:>9.1f} {words_s:>11.0f} {subwd_s:>11.0f} {peak_gb:>8.2f}", flush=True) + + # ETA table from the best (highest words/sec) config. + best_bs, best_words_s = max(results, key=lambda r: r[1]) + hrs_year = CONTEXTUAL_TARGET_TOKENS_PER_YEAR / best_words_s / 3600 + print( + f"\nBest: batch={best_bs} @ {best_words_s:,.0f} words/s", + flush=True, + ) + print( + f"At {CONTEXTUAL_TARGET_TOKENS_PER_YEAR/1e9:.0f}B words/year: " + f"{hrs_year:.1f} h/year, {hrs_year*len(YEARS):.1f} h total " + f"({hrs_year*len(YEARS)/24:.1f} days) over {len(YEARS)} years.", + flush=True, + ) + print( + "Note: words/s drives ETA (corpus target is in words); subwd/s reflects raw GPU load.", + flush=True, + ) + + +if __name__ == "__main__": + main() diff --git a/uv.lock b/uv.lock index 53f90d96a..ed416bb57 100644 --- a/uv.lock +++ b/uv.lock @@ -701,6 +701,7 @@ dependencies = [ { name = "tensorboard" }, { name = "torch" }, { name = "tqdm" }, + { name = "transformers" }, { name = "umap-learn" }, ] @@ -717,6 +718,7 @@ requires-dist = [ { name = "tensorboard", specifier = ">=2.20.0" }, { name = "torch", specifier = ">=2.12.0" }, { name = "tqdm", specifier = ">=4.67.3" }, + { name = "transformers", specifier = ">=5.10.0" }, { name = "umap-learn", specifier = ">=0.5.12" }, ] @@ -1533,6 +1535,78 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/2c/58/ca301544e1fa93ed4f80d724bf5b194f6e4b945841c5bfd555878eea9fcb/referencing-0.37.0-py3-none-any.whl", hash = "sha256:381329a9f99628c9069361716891d34ad94af76e461dcb0335825aecc7692231", size = 26766, upload-time = "2025-10-13T15:30:47.625Z" }, ] +[[package]] +name = "regex" +version = "2026.5.9" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/dc/0e/49aee608ad09480e7fd276898c99ec6192985fa331abe4eb3a986094490b/regex-2026.5.9.tar.gz", hash = "sha256:a8234aa23ec39894bfe4a3f1b85616a7032481964a13ac6fc9f10de4f6fca270", size = 416074, upload-time = "2026-05-09T23:15:19.37Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/aa/da/797e91ecec6f84135da778ddce78c20e0af5d2a15c26f87a81bc3eadb6db/regex-2026.5.9-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:d626b84406444b165fc0ba981604edea39f0588ff1f92baa23fe50799ea9afdb", size = 490303, upload-time = "2026-05-09T23:13:04.382Z" }, + { url = "https://files.pythonhosted.org/packages/44/da/bf30abaaa737b58f4a4b8c4a03659e02fd92092c822e0197ed9e0daab917/regex-2026.5.9-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:d7bdc0ab8f3dd7e1b4f9ab88634e13374669db86bb3c72e8292f07ae313f539f", size = 292019, upload-time = "2026-05-09T23:13:06.022Z" }, + { url = "https://files.pythonhosted.org/packages/2d/e7/d0eaf5713828417b9e5648cf81fa9bacd4961f6ab98c380c2034f8716e35/regex-2026.5.9-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:a8820737949116ffff55fe18f9fc644530063ba6ebfcb8314239416e78f1347c", size = 289468, upload-time = "2026-05-09T23:13:08.214Z" }, + { url = "https://files.pythonhosted.org/packages/d3/9b/b3fdd62b003baa1a9b593cd8c8699c9651c2e80cc21a5c715707983c42d7/regex-2026.5.9-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:aa0fbdbac82cb3e4450d0ccde7d7a35607f4cb2dd9fba4b8b69bfaf8c9fa6aed", size = 796749, upload-time = "2026-05-09T23:13:10.573Z" }, + { url = "https://files.pythonhosted.org/packages/d4/30/66ab84588765f5b4b271a9ca09ef7ce2b87caa95176ec3d2ad65d7bc4902/regex-2026.5.9-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:57e8915c7986aa33d25e4d3629cef711cd2863f2961b10409f0c04cb8b7d9020", size = 865445, upload-time = "2026-05-09T23:13:12.523Z" }, + { url = "https://files.pythonhosted.org/packages/1a/89/f05169e8588aac365f35ffc7f3bc3184f095ef4cfded7cfaa3c7fd5dbd89/regex-2026.5.9-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:508f56a89ba9cb26e4168cbc37dbd60a28d82430a9e18ad1d25fe0883c314ca2", size = 912322, upload-time = "2026-05-09T23:13:14.281Z" }, + { url = "https://files.pythonhosted.org/packages/30/e1/c93444052cf41581f3c884ab3fb5823daf0992f11cd4388d4275ca610558/regex-2026.5.9-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:b6d189041f15691cfa2b6c4290448ec221244d225b3f5fe9e7771b34ffcdf6e2", size = 801269, upload-time = "2026-05-09T23:13:16.569Z" }, + { url = "https://files.pythonhosted.org/packages/50/fe/0cf96b882f540e62e8b9956599798203d599c44cf4c77917ca27400ff69b/regex-2026.5.9-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:e82db382b44d0111b22601c509c89f64434816c9e0eef9d1989cda8cc6ff1c04", size = 777085, upload-time = "2026-05-09T23:13:18.675Z" }, + { url = "https://files.pythonhosted.org/packages/23/5c/d78d4924e7fc875557b9e9b768423925fdfaac5549d06da7810019a9bd26/regex-2026.5.9-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:2acfb48634f64996b57f90f39afa692ff362162722581921fe92239a59960f3c", size = 785153, upload-time = "2026-05-09T23:13:20.525Z" }, + { url = "https://files.pythonhosted.org/packages/bf/e0/5214774090e7b4524dcea3e3c4aa74141d43043f8beb49c1599db1c8b53a/regex-2026.5.9-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:d29eebfc9525db68cad3c97eedd7f754fa265aa5cd0cf4f863b2421e1b48fc9f", size = 860164, upload-time = "2026-05-09T23:13:22.263Z" }, + { url = "https://files.pythonhosted.org/packages/6e/e1/4a57a83350319b1271f0d7a249b8672513ed928b237a741631270de6caea/regex-2026.5.9-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:debb893095e944091c16e641a6e33c1b0f4cb61ab945ec5afbf53ce7068834d8", size = 765731, upload-time = "2026-05-09T23:13:24.277Z" }, + { url = "https://files.pythonhosted.org/packages/12/f4/499e74a20c156fc75836ee04a72a38d1a063978f600937f9760467beb1b0/regex-2026.5.9-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:d659eee77986549c9ea45b861c7567e44d6287c3dc9a4565478853f7b9fe2ff6", size = 852062, upload-time = "2026-05-09T23:13:26.125Z" }, + { url = "https://files.pythonhosted.org/packages/5b/92/7eebc0d0a01e78629695f342ba17e0deaff8fb45e79cc0d7b98287da6e3e/regex-2026.5.9-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:2efa205e6d98b24d1f3ab395c11aa15cdf10935bca283d0285e0499c284fba21", size = 789577, upload-time = "2026-05-09T23:13:27.814Z" }, + { url = "https://files.pythonhosted.org/packages/05/a4/018e71f7d2ad48c1ebe6d3ae0026f9b7cb4802fd15c7cc02fdf724355102/regex-2026.5.9-cp313-cp313-win32.whl", hash = "sha256:f3844f134e834076677dd369976e9f5068679fcb8e50102fdf6b7ac96a3ec127", size = 266691, upload-time = "2026-05-09T23:13:29.549Z" }, + { url = "https://files.pythonhosted.org/packages/e6/1d/861a93719fb9ee7dbfc3761b3797b7a3e112a5d42c6129459d2d741be9b5/regex-2026.5.9-cp313-cp313-win_amd64.whl", hash = "sha256:3527bb4942d2c14552155406cdedd906567456821848aed1cb4933a391bf5eca", size = 277747, upload-time = "2026-05-09T23:13:31.859Z" }, + { url = "https://files.pythonhosted.org/packages/d9/c6/0a2436ae4da1ba76e51cb98943c6838a9a721faa40ebe2dce07694ae34e3/regex-2026.5.9-cp313-cp313-win_arm64.whl", hash = "sha256:56a33f191f17d8c417f99945ebdc1e691d3af9605d86ec68c7e54a57e3e17af6", size = 270500, upload-time = "2026-05-09T23:13:33.525Z" }, + { url = "https://files.pythonhosted.org/packages/e8/e9/d21346f7b60ed58789371358ed66b09d00f832e1bd7c06e55d9da5679882/regex-2026.5.9-cp313-cp313t-macosx_10_13_universal2.whl", hash = "sha256:01f28d868834624c934b8d2e0aa1c8341337e37831f4a012f18a5afcba4cbaf3", size = 494172, upload-time = "2026-05-09T23:13:35.935Z" }, + { url = "https://files.pythonhosted.org/packages/c4/43/fd1177a2032037c681baecdb3422ee4e1424aec4e4f470ef47793d325274/regex-2026.5.9-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:48036f6374aaa79eb3b754ec29c61d1c6b1606749d705a13f8854fa2539671f6", size = 293952, upload-time = "2026-05-09T23:13:38.307Z" }, + { url = "https://files.pythonhosted.org/packages/f2/7d/9fbf919768368d3f8a4f6c692cf2aa61e482b2b81ec6a298ace4cbf02480/regex-2026.5.9-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:b96350aa424e79d4fd6b567b344dcbe2b2d6bfc48dfe7717587e1fa6d43da6ff", size = 292314, upload-time = "2026-05-09T23:13:40.353Z" }, + { url = "https://files.pythonhosted.org/packages/e2/6c/e41bfeecb589716843e7c4df09ba46ff2a42961457afece19059d85caeef/regex-2026.5.9-cp313-cp313t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8f3af7a4903c5c04a11a196a5aa75cdd7dd3f8508132f9fb3259d9f5908e3b88", size = 811681, upload-time = "2026-05-09T23:13:42.543Z" }, + { url = "https://files.pythonhosted.org/packages/87/83/a5c1c525fba0aa656e88ad0face0b1829788ef4c2fb6b26df58aa1151b84/regex-2026.5.9-cp313-cp313t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:7e87577720152d2caae19fe2baaf1f8d5ca12091e9e229f03915c37d1e4b9178", size = 871135, upload-time = "2026-05-09T23:13:44.326Z" }, + { url = "https://files.pythonhosted.org/packages/18/d4/80882e799e440dd878b0979cbebf8fa4d54624a332c83037c7a701649e3f/regex-2026.5.9-cp313-cp313t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:c8b9b9d294cfea3cd19c718ade7cc93492b2c4991abd9a68d0b3477ae6d8e100", size = 917265, upload-time = "2026-05-09T23:13:47.295Z" }, + { url = "https://files.pythonhosted.org/packages/ae/ff/8db60211e2286e396aad7dc7725356c502bff0901ea05bd6cdc2e1a042b9/regex-2026.5.9-cp313-cp313t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:728d8bfd28a8845c8b6bc5dc7ce010453d206396786c0765c2740cb65f37791e", size = 816311, upload-time = "2026-05-09T23:13:49.885Z" }, + { url = "https://files.pythonhosted.org/packages/4c/47/742ef579c61730f8d268e5cf1f9ce0e37e2ea041ad0f5644724f2378e463/regex-2026.5.9-cp313-cp313t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:7e30b874d341fac767d7df5a0870540541c2c054b80cfaac116e8d367a8a7ff2", size = 785498, upload-time = "2026-05-09T23:13:52.25Z" }, + { url = "https://files.pythonhosted.org/packages/7f/ab/cb0999802dcb0fb95b1ab005e8d4163d8afdd67efc2cb6b6630ac13f8cb1/regex-2026.5.9-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:fd190e88a895a8901325fad284a3f74ea52b1da8525b76cc811fa9b1edf0ce2b", size = 801348, upload-time = "2026-05-09T23:13:54.127Z" }, + { url = "https://files.pythonhosted.org/packages/7d/62/8ca59a24c55bc34d166eefaf3717bd77772f329fdbf984d86581e0a3571c/regex-2026.5.9-cp313-cp313t-musllinux_1_2_ppc64le.whl", hash = "sha256:8e76e8161ad00694cfce6767d5dea860c6391ac5b83e5c3a39661e696f11fc7e", size = 866493, upload-time = "2026-05-09T23:13:56.067Z" }, + { url = "https://files.pythonhosted.org/packages/8d/3d/30f2ae62cef3278bb5bb821f467277a55fb73f01032cf85997e15e8289a8/regex-2026.5.9-cp313-cp313t-musllinux_1_2_riscv64.whl", hash = "sha256:ddda5340e6c01a293027dd46232fa79eaff1b48058ce7a98f572b6445b088041", size = 772811, upload-time = "2026-05-09T23:13:57.867Z" }, + { url = "https://files.pythonhosted.org/packages/d8/ae/7d2089bcd78ad0c0161bc684339df50032acb438a7bd3305e7ddb1193cec/regex-2026.5.9-cp313-cp313t-musllinux_1_2_s390x.whl", hash = "sha256:205109e96b3cf5adf8f4cd62bedde9487feb282b9497a3535451e5a24cd706a0", size = 856584, upload-time = "2026-05-09T23:13:59.679Z" }, + { url = "https://files.pythonhosted.org/packages/a9/29/92ff47f75990131ea4f24ba17819e5a9d141e10819807e09addd73409af6/regex-2026.5.9-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:dfbe4579b9f08036aa7d101d1835437a20783574ac66327e6b29b4018a138081", size = 803453, upload-time = "2026-05-09T23:14:01.978Z" }, + { url = "https://files.pythonhosted.org/packages/04/99/eff29f1037dcab36702c9ee5d6858cf1ce2336ea8ea2987f64245b99ea5e/regex-2026.5.9-cp313-cp313t-win32.whl", hash = "sha256:ed2c9e8068b614c574d8d30e543d617cf5379b0535d46f97ef00e904745a08b5", size = 269951, upload-time = "2026-05-09T23:14:03.661Z" }, + { url = "https://files.pythonhosted.org/packages/0e/9d/8870b8981d27b22cda77bb26a5ac7ebfa9c7d9e0dea195a834a82380e748/regex-2026.5.9-cp313-cp313t-win_amd64.whl", hash = "sha256:b46b0f094dc1d3b90356c85a0bd2c9bafc4a6a190b9d6f8ddd5a033b6e088ed4", size = 281240, upload-time = "2026-05-09T23:14:05.56Z" }, + { url = "https://files.pythonhosted.org/packages/72/b1/3379415e8f135c13ac551353397cc4fe97b4978f3cac73c5fcbcded548b8/regex-2026.5.9-cp313-cp313t-win_arm64.whl", hash = "sha256:872acc074bd29ffc9913ecdfedf6ea77502312ca44a4aa0d3779089c6069d8de", size = 272383, upload-time = "2026-05-09T23:14:07.843Z" }, + { url = "https://files.pythonhosted.org/packages/13/3e/9c3cd292d8808b3645a2ce517e200179b6d0e903f176300bd8b542e14de5/regex-2026.5.9-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:1bd7587a2948b4085195d5a3374eaf4a425dc3e55784c038175355ecf3bbbf8a", size = 490376, upload-time = "2026-05-09T23:14:09.64Z" }, + { url = "https://files.pythonhosted.org/packages/60/70/d43ee8a2ca0a8b68d167f21658b85520ac0574617c7f320367c5047f7556/regex-2026.5.9-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:dea2e88e1cce4522496cce630e11e67b98b7076620bc4336c3f674bc21a375f4", size = 291964, upload-time = "2026-05-09T23:14:11.424Z" }, + { url = "https://files.pythonhosted.org/packages/21/91/9d50b433828d8e74196904e168a43abf1e6e88b2a15d47ed742456720c37/regex-2026.5.9-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:2099f7e7ff7b6aa3192312650a56e91cc091e49d50b04e4f6f8b6e28b3b27f1c", size = 289682, upload-time = "2026-05-09T23:14:13.123Z" }, + { url = "https://files.pythonhosted.org/packages/3e/d2/b835e3cafbb9d977736912436259ff551d60919f7d7b3d37d46659c63564/regex-2026.5.9-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:ecd353045824e4477562a2ac718c25799cdaaa41f7aa925a806a8a3e6848a5b9", size = 796996, upload-time = "2026-05-09T23:14:14.923Z" }, + { url = "https://files.pythonhosted.org/packages/2c/a6/9f992d00019166b9de01c546dd4549bc679f2a68df11b877740b0760b7c2/regex-2026.5.9-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:65c8c8c37377794bd5b2f3ebe51919042bf17aec802e23c833d89782ed0c78af", size = 866089, upload-time = "2026-05-09T23:14:17.757Z" }, + { url = "https://files.pythonhosted.org/packages/e0/08/4d32af657e049b19cb62b02e46e38fe1518797bfb2203ee93a510b21b0dc/regex-2026.5.9-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:5b73ab8afcf66c622db143d1c6fda4e58e4d537ee4f125229ad47b1ab80f34c0", size = 911530, upload-time = "2026-05-09T23:14:20.353Z" }, + { url = "https://files.pythonhosted.org/packages/d9/27/2af43dd1dc201d1fecefda64a45f4ad0995855b92724f795a777b402ee69/regex-2026.5.9-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0de5cf193997384ed2ca6f1cd4f78055b255d93d82d5a8cd6ba0d11c10b167e4", size = 800643, upload-time = "2026-05-09T23:14:22.265Z" }, + { url = "https://files.pythonhosted.org/packages/a4/dd/23a249047013b5321d4a60c4d2437462086f601b061776a525e5fba2a59f/regex-2026.5.9-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:d641a8c9a61618047796d572a39a79b26167b0411d2c3031937b2fe2d081e2cf", size = 777223, upload-time = "2026-05-09T23:14:24.179Z" }, + { url = "https://files.pythonhosted.org/packages/94/6a/e85ed9538cd19586d0465076a4578a12e093ce776d15f3f8ce92733a8dd6/regex-2026.5.9-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:24b2355ef5cc9aa5b8f07d17704face1c166fdcc2290fa7bd6e6c925655a8346", size = 785760, upload-time = "2026-05-09T23:14:26.065Z" }, + { url = "https://files.pythonhosted.org/packages/2a/c4/f25473209438638e947c55f9156fd8f236f74169229028cc99116380868e/regex-2026.5.9-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:a24852d3c29ad9e47593593d8a247c44ccc3d0548ef12c822d6ed0810affe676", size = 860891, upload-time = "2026-05-09T23:14:28.17Z" }, + { url = "https://files.pythonhosted.org/packages/f9/f7/f4f86e3c74419c37370e91f150ae0c2ef7d34b2e0e4cdd5da046a02e4022/regex-2026.5.9-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:916714069da19329ef7de197dcbc77bb3104145c7c2c864dbfbe318f46b88b14", size = 765891, upload-time = "2026-05-09T23:14:30.06Z" }, + { url = "https://files.pythonhosted.org/packages/26/70/704d8e13765939146b1cd0ef4e2feb71d7929727d2290f026eed10095955/regex-2026.5.9-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:fa411799ca8da32a8d38d020a88faa5b6f91657d284761352940ecf9f7c3bbdd", size = 851380, upload-time = "2026-05-09T23:14:32.123Z" }, + { url = "https://files.pythonhosted.org/packages/26/29/1a13582a8460038edc38e49f64ceb0dd7c60f5caba77571f4bf6601965d9/regex-2026.5.9-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:1e6da47d679b7010ef27556b6e0f99771b744936db1792a10ceac6547ae1503e", size = 789350, upload-time = "2026-05-09T23:14:34.799Z" }, + { url = "https://files.pythonhosted.org/packages/73/56/3dcafe34fc72e271d62ad9a291801e88a1457bb251c132f15fcc2e5aad1a/regex-2026.5.9-cp314-cp314-win32.whl", hash = "sha256:98bd73080e8756255137e1bd3f3f00295bbc5aa383c0e0f973920e9134d7c4ad", size = 272130, upload-time = "2026-05-09T23:14:36.729Z" }, + { url = "https://files.pythonhosted.org/packages/d0/9c/02eebf0be95efe416c664db7fb8b6b05b7a0b06a7544f2884f2558b0526f/regex-2026.5.9-cp314-cp314-win_amd64.whl", hash = "sha256:ff8d372ac2acdc048d1c19916f27ee61bc5722728458ba6ca5052f2c72d51763", size = 280999, upload-time = "2026-05-09T23:14:39.126Z" }, + { url = "https://files.pythonhosted.org/packages/70/5a/1dd1abee76cb7a846a0bcf42fdc87e5720c3c33c24f3e37814310a513d9f/regex-2026.5.9-cp314-cp314-win_arm64.whl", hash = "sha256:e1d93bf647916292e8edcec150c07ddf3dc50179ccaf770c04a7f9e452155372", size = 273500, upload-time = "2026-05-09T23:14:41.059Z" }, + { url = "https://files.pythonhosted.org/packages/86/c1/c5f619b0057a7965cb78ec559c1d7a45ce8c99a35bea95483d64959a93d9/regex-2026.5.9-cp314-cp314t-macosx_10_13_universal2.whl", hash = "sha256:83d0ee4a57d1c87cb549e195ec300b8f0ec3a82eba66d835e4e2ed8634fe4499", size = 494269, upload-time = "2026-05-09T23:14:42.869Z" }, + { url = "https://files.pythonhosted.org/packages/05/2c/5d01f1aee33de4bbe60c8452945bfc8477ca7c5ae4450f6bfe711036cb36/regex-2026.5.9-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:d3d7eb5c9a7f6df82ed3cfac9beb93882a5cbcb5b8b157b56cb2b3b276574ac1", size = 293954, upload-time = "2026-05-09T23:14:44.822Z" }, + { url = "https://files.pythonhosted.org/packages/7a/fe/e8988b2ae2108c6ef71bd4aa8d87fbe257976dd0810e826cd75f701c68b6/regex-2026.5.9-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:075160bf16658e16d35233300b8453aac25de4cbea808d22348b6979668e924d", size = 292405, upload-time = "2026-05-09T23:14:47.211Z" }, + { url = "https://files.pythonhosted.org/packages/79/34/d2b0937faa7859263f7f0a3c6b103a1296306be6952dc173d0154e9a2f49/regex-2026.5.9-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:45375819235558a4ff1c4971dc32881f022613abdb180128f5cb4768c1765a1c", size = 811855, upload-time = "2026-05-09T23:14:49.21Z" }, + { url = "https://files.pythonhosted.org/packages/80/fe/daf53a47457a8486db66c66c01ceb9c2303eecee3f87197f1e77eb1a736d/regex-2026.5.9-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:ead4b163ac30a29574510cd4b3e2e985ac5290c05fc7095557d6a5f403fc31b5", size = 871189, upload-time = "2026-05-09T23:14:51.555Z" }, + { url = "https://files.pythonhosted.org/packages/1c/75/058fc4470cbfbf57d800aff1a0022b929a3f9fa553ee10a0cdf2070eb31f/regex-2026.5.9-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:8c6e4218fbdfbcd4f6c19efca40930d24a621bf4b48cb76bc6640543bd28ef20", size = 917485, upload-time = "2026-05-09T23:14:53.633Z" }, + { url = "https://files.pythonhosted.org/packages/88/e7/179cfda3a28bc843b5c6cfe7f79f23489c791ed95f151083803660878432/regex-2026.5.9-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:6351571c8a42b505eb555c0dc47d740d0fb66977dc142919eea6f4325b7c56a0", size = 816369, upload-time = "2026-05-09T23:14:56.198Z" }, + { url = "https://files.pythonhosted.org/packages/41/90/6f0cc422071688266d344fca8462d787cba0a2c144acb25721f9a61ec265/regex-2026.5.9-cp314-cp314t-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:002205cafd2a9e78c6290c7d1df277bf3277b3b7a30e0b4bb0dac2e2e3f7cb2d", size = 785869, upload-time = "2026-05-09T23:14:58.602Z" }, + { url = "https://files.pythonhosted.org/packages/02/67/a31f1760f09c27b251ef39e9beb541f462cf977381d067faa764c2c0e393/regex-2026.5.9-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:8abd33fef90b2a9efac5557d6033ca82d1195ed3a15fea5af15ba7b463c6a63b", size = 801427, upload-time = "2026-05-09T23:15:00.642Z" }, + { url = "https://files.pythonhosted.org/packages/e3/c4/1a80654597b6bc1e1ea0494824c31200e8a956abe290afae9b19a166a148/regex-2026.5.9-cp314-cp314t-musllinux_1_2_ppc64le.whl", hash = "sha256:31037c82eccb44b7ea2e9e221d7c01429430e989a1f4b91ea5a855f6017b509a", size = 866482, upload-time = "2026-05-09T23:15:03.384Z" }, + { url = "https://files.pythonhosted.org/packages/d1/11/960724e06482c08466ff5611e242e86f80062949cdf6b4b9cc317b9dd93d/regex-2026.5.9-cp314-cp314t-musllinux_1_2_riscv64.whl", hash = "sha256:5604dfd046dc37eca90250fc3be938b076c8059fa772ac0ed6f499b0f0fb0415", size = 773022, upload-time = "2026-05-09T23:15:05.625Z" }, + { url = "https://files.pythonhosted.org/packages/50/a8/a9979c3e7918280e93159ebcab5ef1a65116dd4f3bd6091be0eae4a126e8/regex-2026.5.9-cp314-cp314t-musllinux_1_2_s390x.whl", hash = "sha256:0e1b1b4e496afbb24f4a62aba855ee4f88f25578927697b340702e48c9ee6bc2", size = 856642, upload-time = "2026-05-09T23:15:07.966Z" }, + { url = "https://files.pythonhosted.org/packages/fe/d4/a9b732f2f0072c0ab12227483abb24fffcb9f73f8a2b203df0a6d0434735/regex-2026.5.9-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:be3372b9df6ddecff6486d37e19095a7b4973137caf5512407a89f4455361f41", size = 803552, upload-time = "2026-05-09T23:15:10.215Z" }, + { url = "https://files.pythonhosted.org/packages/d5/fe/1b3113817447a1d4155e4ac76d2e072f42c0bcba2f43fa8a0e756ea2cd91/regex-2026.5.9-cp314-cp314t-win32.whl", hash = "sha256:3ddd90103f9e5c471c49c7852ecc1fe27c7e45eb99e977aefe7caa4e779f4f58", size = 275746, upload-time = "2026-05-09T23:15:12.609Z" }, + { url = "https://files.pythonhosted.org/packages/92/73/93d42045302636c91f2e5ef588b65b84b01428f28ec77de256b1dfdfbe5c/regex-2026.5.9-cp314-cp314t-win_amd64.whl", hash = "sha256:ca518ed29c46eecba6010b15f1b9a479314d2de409536e71b6a13aa04e3b8a77", size = 285685, upload-time = "2026-05-09T23:15:15.086Z" }, + { url = "https://files.pythonhosted.org/packages/da/80/35b4c33c804a165a7f55289afda3ea9e3eb6d15800341a2d66455c0f1f30/regex-2026.5.9-cp314-cp314t-win_arm64.whl", hash = "sha256:5e41809d2683fcde7d5a8c87a6567ba1fb1ce0de9f31bff578de00a4b2d76daa", size = 275713, upload-time = "2026-05-09T23:15:16.98Z" }, +] + [[package]] name = "requests" version = "2.34.2" @@ -1627,6 +1701,28 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/d0/02/fa464cdfbe6b26e0600b62c528b72d8608f5cc49f96b8d6e38c95d60c676/rpds_py-0.30.0-cp314-cp314t-win_amd64.whl", hash = "sha256:27f4b0e92de5bfbc6f86e43959e6edd1425c33b5e69aab0984a72047f2bcf1e3", size = 226532, upload-time = "2025-11-30T20:24:14.634Z" }, ] +[[package]] +name = "safetensors" +version = "0.7.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/29/9c/6e74567782559a63bd040a236edca26fd71bc7ba88de2ef35d75df3bca5e/safetensors-0.7.0.tar.gz", hash = "sha256:07663963b67e8bd9f0b8ad15bb9163606cd27cc5a1b96235a50d8369803b96b0", size = 200878, upload-time = "2025-11-19T15:18:43.199Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/fa/47/aef6c06649039accf914afef490268e1067ed82be62bcfa5b7e886ad15e8/safetensors-0.7.0-cp38-abi3-macosx_10_12_x86_64.whl", hash = "sha256:c82f4d474cf725255d9e6acf17252991c3c8aac038d6ef363a4bf8be2f6db517", size = 467781, upload-time = "2025-11-19T15:18:35.84Z" }, + { url = "https://files.pythonhosted.org/packages/e8/00/374c0c068e30cd31f1e1b46b4b5738168ec79e7689ca82ee93ddfea05109/safetensors-0.7.0-cp38-abi3-macosx_11_0_arm64.whl", hash = "sha256:94fd4858284736bb67a897a41608b5b0c2496c9bdb3bf2af1fa3409127f20d57", size = 447058, upload-time = "2025-11-19T15:18:34.416Z" }, + { url = "https://files.pythonhosted.org/packages/f1/06/578ffed52c2296f93d7fd2d844cabfa92be51a587c38c8afbb8ae449ca89/safetensors-0.7.0-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e07d91d0c92a31200f25351f4acb2bc6aff7f48094e13ebb1d0fb995b54b6542", size = 491748, upload-time = "2025-11-19T15:18:09.79Z" }, + { url = "https://files.pythonhosted.org/packages/ae/33/1debbbb70e4791dde185edb9413d1fe01619255abb64b300157d7f15dddd/safetensors-0.7.0-cp38-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8469155f4cb518bafb4acf4865e8bb9d6804110d2d9bdcaa78564b9fd841e104", size = 503881, upload-time = "2025-11-19T15:18:16.145Z" }, + { url = "https://files.pythonhosted.org/packages/8e/1c/40c2ca924d60792c3be509833df711b553c60effbd91da6f5284a83f7122/safetensors-0.7.0-cp38-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:54bef08bf00a2bff599982f6b08e8770e09cc012d7bba00783fc7ea38f1fb37d", size = 623463, upload-time = "2025-11-19T15:18:21.11Z" }, + { url = "https://files.pythonhosted.org/packages/9b/3a/13784a9364bd43b0d61eef4bea2845039bc2030458b16594a1bd787ae26e/safetensors-0.7.0-cp38-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:42cb091236206bb2016d245c377ed383aa7f78691748f3bb6ee1bfa51ae2ce6a", size = 532855, upload-time = "2025-11-19T15:18:25.719Z" }, + { url = "https://files.pythonhosted.org/packages/a0/60/429e9b1cb3fc651937727befe258ea24122d9663e4d5709a48c9cbfceecb/safetensors-0.7.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dac7252938f0696ddea46f5e855dd3138444e82236e3be475f54929f0c510d48", size = 507152, upload-time = "2025-11-19T15:18:33.023Z" }, + { url = "https://files.pythonhosted.org/packages/3c/a8/4b45e4e059270d17af60359713ffd83f97900d45a6afa73aaa0d737d48b6/safetensors-0.7.0-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:1d060c70284127fa805085d8f10fbd0962792aed71879d00864acda69dbab981", size = 541856, upload-time = "2025-11-19T15:18:31.075Z" }, + { url = "https://files.pythonhosted.org/packages/06/87/d26d8407c44175d8ae164a95b5a62707fcc445f3c0c56108e37d98070a3d/safetensors-0.7.0-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:cdab83a366799fa730f90a4ebb563e494f28e9e92c4819e556152ad55e43591b", size = 674060, upload-time = "2025-11-19T15:18:37.211Z" }, + { url = "https://files.pythonhosted.org/packages/11/f5/57644a2ff08dc6325816ba7217e5095f17269dada2554b658442c66aed51/safetensors-0.7.0-cp38-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:672132907fcad9f2aedcb705b2d7b3b93354a2aec1b2f706c4db852abe338f85", size = 771715, upload-time = "2025-11-19T15:18:38.689Z" }, + { url = "https://files.pythonhosted.org/packages/86/31/17883e13a814bd278ae6e266b13282a01049b0c81341da7fd0e3e71a80a3/safetensors-0.7.0-cp38-abi3-musllinux_1_2_i686.whl", hash = "sha256:5d72abdb8a4d56d4020713724ba81dac065fedb7f3667151c4a637f1d3fb26c0", size = 714377, upload-time = "2025-11-19T15:18:40.162Z" }, + { url = "https://files.pythonhosted.org/packages/4a/d8/0c8a7dc9b41dcac53c4cbf9df2b9c83e0e0097203de8b37a712b345c0be5/safetensors-0.7.0-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:b0f6d66c1c538d5a94a73aa9ddca8ccc4227e6c9ff555322ea40bdd142391dd4", size = 677368, upload-time = "2025-11-19T15:18:41.627Z" }, + { url = "https://files.pythonhosted.org/packages/05/e5/cb4b713c8a93469e3c5be7c3f8d77d307e65fe89673e731f5c2bfd0a9237/safetensors-0.7.0-cp38-abi3-win32.whl", hash = "sha256:c74af94bf3ac15ac4d0f2a7c7b4663a15f8c2ab15ed0fc7531ca61d0835eccba", size = 326423, upload-time = "2025-11-19T15:18:45.74Z" }, + { url = "https://files.pythonhosted.org/packages/5d/e6/ec8471c8072382cb91233ba7267fd931219753bb43814cbc71757bfd4dab/safetensors-0.7.0-cp38-abi3-win_amd64.whl", hash = "sha256:d1239932053f56f3456f32eb9625590cc7582e905021f94636202a864d470755", size = 341380, upload-time = "2025-11-19T15:18:44.427Z" }, +] + [[package]] name = "scikit-learn" version = "1.8.0" @@ -1859,6 +1955,32 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/32/d5/f9a850d79b0851d1d4ef6456097579a9005b31fea68726a4ae5f2d82ddd9/threadpoolctl-3.6.0-py3-none-any.whl", hash = "sha256:43a0b8fd5a2928500110039e43a5eed8480b918967083ea48dc3ab9f13c4a7fb", size = 18638, upload-time = "2025-03-13T13:49:21.846Z" }, ] +[[package]] +name = "tokenizers" +version = "0.22.2" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "huggingface-hub" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/73/6f/f80cfef4a312e1fb34baf7d85c72d4411afde10978d4657f8cdd811d3ccc/tokenizers-0.22.2.tar.gz", hash = "sha256:473b83b915e547aa366d1eee11806deaf419e17be16310ac0a14077f1e28f917", size = 372115, upload-time = "2026-01-05T10:45:15.988Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/92/97/5dbfabf04c7e348e655e907ed27913e03db0923abb5dfdd120d7b25630e1/tokenizers-0.22.2-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:544dd704ae7238755d790de45ba8da072e9af3eea688f698b137915ae959281c", size = 3100275, upload-time = "2026-01-05T10:41:02.158Z" }, + { url = "https://files.pythonhosted.org/packages/2e/47/174dca0502ef88b28f1c9e06b73ce33500eedfac7a7692108aec220464e7/tokenizers-0.22.2-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:1e418a55456beedca4621dbab65a318981467a2b188e982a23e117f115ce5001", size = 2981472, upload-time = "2026-01-05T10:41:00.276Z" }, + { url = "https://files.pythonhosted.org/packages/d6/84/7990e799f1309a8b87af6b948f31edaa12a3ed22d11b352eaf4f4b2e5753/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2249487018adec45d6e3554c71d46eb39fa8ea67156c640f7513eb26f318cec7", size = 3290736, upload-time = "2026-01-05T10:40:32.165Z" }, + { url = "https://files.pythonhosted.org/packages/78/59/09d0d9ba94dcd5f4f1368d4858d24546b4bdc0231c2354aa31d6199f0399/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:25b85325d0815e86e0bac263506dd114578953b7b53d7de09a6485e4a160a7dd", size = 3168835, upload-time = "2026-01-05T10:40:38.847Z" }, + { url = "https://files.pythonhosted.org/packages/47/50/b3ebb4243e7160bda8d34b731e54dd8ab8b133e50775872e7a434e524c28/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bfb88f22a209ff7b40a576d5324bf8286b519d7358663db21d6246fb17eea2d5", size = 3521673, upload-time = "2026-01-05T10:40:56.614Z" }, + { url = "https://files.pythonhosted.org/packages/e0/fa/89f4cb9e08df770b57adb96f8cbb7e22695a4cb6c2bd5f0c4f0ebcf33b66/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1c774b1276f71e1ef716e5486f21e76333464f47bece56bbd554485982a9e03e", size = 3724818, upload-time = "2026-01-05T10:40:44.507Z" }, + { url = "https://files.pythonhosted.org/packages/64/04/ca2363f0bfbe3b3d36e95bf67e56a4c88c8e3362b658e616d1ac185d47f2/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:df6c4265b289083bf710dff49bc51ef252f9d5be33a45ee2bed151114a56207b", size = 3379195, upload-time = "2026-01-05T10:40:51.139Z" }, + { url = "https://files.pythonhosted.org/packages/2e/76/932be4b50ef6ccedf9d3c6639b056a967a86258c6d9200643f01269211ca/tokenizers-0.22.2-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:369cc9fc8cc10cb24143873a0d95438bb8ee257bb80c71989e3ee290e8d72c67", size = 3274982, upload-time = "2026-01-05T10:40:58.331Z" }, + { url = "https://files.pythonhosted.org/packages/1d/28/5f9f5a4cc211b69e89420980e483831bcc29dade307955cc9dc858a40f01/tokenizers-0.22.2-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:29c30b83d8dcd061078b05ae0cb94d3c710555fbb44861139f9f83dcca3dc3e4", size = 9478245, upload-time = "2026-01-05T10:41:04.053Z" }, + { url = "https://files.pythonhosted.org/packages/6c/fb/66e2da4704d6aadebf8cb39f1d6d1957df667ab24cff2326b77cda0dcb85/tokenizers-0.22.2-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:37ae80a28c1d3265bb1f22464c856bd23c02a05bb211e56d0c5301a435be6c1a", size = 9560069, upload-time = "2026-01-05T10:45:10.673Z" }, + { url = "https://files.pythonhosted.org/packages/16/04/fed398b05caa87ce9b1a1bb5166645e38196081b225059a6edaff6440fac/tokenizers-0.22.2-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:791135ee325f2336f498590eb2f11dc5c295232f288e75c99a36c5dbce63088a", size = 9899263, upload-time = "2026-01-05T10:45:12.559Z" }, + { url = "https://files.pythonhosted.org/packages/05/a1/d62dfe7376beaaf1394917e0f8e93ee5f67fea8fcf4107501db35996586b/tokenizers-0.22.2-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:38337540fbbddff8e999d59970f3c6f35a82de10053206a7562f1ea02d046fa5", size = 10033429, upload-time = "2026-01-05T10:45:14.333Z" }, + { url = "https://files.pythonhosted.org/packages/fd/18/a545c4ea42af3df6effd7d13d250ba77a0a86fb20393143bbb9a92e434d4/tokenizers-0.22.2-cp39-abi3-win32.whl", hash = "sha256:a6bf3f88c554a2b653af81f3204491c818ae2ac6fbc09e76ef4773351292bc92", size = 2502363, upload-time = "2026-01-05T10:45:20.593Z" }, + { url = "https://files.pythonhosted.org/packages/65/71/0670843133a43d43070abeb1949abfdef12a86d490bea9cd9e18e37c5ff7/tokenizers-0.22.2-cp39-abi3-win_amd64.whl", hash = "sha256:c9ea31edff2968b44a88f97d784c2f16dc0729b8b143ed004699ebca91f05c48", size = 2747786, upload-time = "2026-01-05T10:45:18.411Z" }, + { url = "https://files.pythonhosted.org/packages/72/f4/0de46cfa12cdcbcd464cc59fde36912af405696f687e53a091fb432f694c/tokenizers-0.22.2-cp39-abi3-win_arm64.whl", hash = "sha256:9ce725d22864a1e965217204946f830c37876eee3b2ba6fc6255e8e903d5fcbc", size = 2612133, upload-time = "2026-01-05T10:45:17.232Z" }, +] + [[package]] name = "toml" version = "0.10.2" @@ -1920,6 +2042,26 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/16/e1/3079a9ff9b8e11b846c6ac5c8b5bfb7ff225eee721825310c91b3b50304f/tqdm-4.67.3-py3-none-any.whl", hash = "sha256:ee1e4c0e59148062281c49d80b25b67771a127c85fc9676d3be5f243206826bf", size = 78374, upload-time = "2026-02-03T17:35:50.982Z" }, ] +[[package]] +name = "transformers" +version = "5.10.2" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "huggingface-hub" }, + { name = "numpy" }, + { name = "packaging" }, + { name = "pyyaml" }, + { name = "regex" }, + { name = "safetensors" }, + { name = "tokenizers" }, + { name = "tqdm" }, + { name = "typer" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/8d/38/d5f978bd5091019e89aef29b9a831f5cd70f2598963a3ead8b9570cab592/transformers-5.10.2.tar.gz", hash = "sha256:f9a44b9c8ca9ab1156b467f574d832ea066284299c2fd0ed84641ccb592751fc", size = 8799687, upload-time = "2026-06-04T18:43:49.119Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/73/6f/e1564b0cc182afa05e219a8e09a8e770ffaab879b6b824b56c819bd221da/transformers-5.10.2-py3-none-any.whl", hash = "sha256:8a669db546f82c7c3618cb46ceb0f0afd89292bc70f319c058f8332ec63e268d", size = 11003830, upload-time = "2026-06-04T18:43:45.303Z" }, +] + [[package]] name = "triton" version = "3.7.0"