mlboydaisuke/ms-marco-MiniLM-L12-v2-ExecuTorch

ms-marco-MiniLM-L12-v2 — ExecuTorch

A cross-encoder reranker: a query and one document in, one relevance score out. The second stage of on-device retrieval — an embedding model fetches candidates cheaply, this reads each candidate together with the query and scores it properly.

• Source: cross-encoder/ms-marco-MiniLM-L12-v2 — 33.4M parameters, 12 BERT layers, hidden 384
• License: Apache-2.0
• Input: input_ids, attention_mask and token_type_ids, each [1, 512] int64
• Output: [1, 1] fp32 — the raw logit. sigmoid(x) maps it to 0..1 and does not change the ordering.

Variants

build	file	size (MB)	worst score error vs eager	Mac median (ms)*	backend takes
fp32	rerank_ms_marco_minilm_l12_xnnpack_fp32.pte	133.6	0.0000 logits	32.7	80.0%
fp16	rerank_ms_marco_minilm_l12_xnnpack_fp16.pte	66.9	0.0070 logits	51.5	69.0%
Core ML (fp16, iOS)	rerank_ms_marco_minilm_l12_coreml_all.pte	68.3	0.0369 logits	13.1	100.0%

*Mac arm64, one query-document pair at 512 tokens, fastest of five medians of ten — a reference point for relative cost, not a device number. The host shares its cores with other work, and a single median does not survive that; contention only ever adds time, so the fastest repetition is the one that means something. PyTorch eager fp32, measured the same way: 33.9 ms.

Correlation is not reported because it cannot be: the output is a single number, and the correlation of a one-element vector is undefined. The column above is the error in the units the model is used in — logits — over 6 real query-document pairs, and every build listed reproduces eager's ranking order exactly.

What it does, on the shipped fp32 build

Query: "How many people live in Berlin?"

rank	score	document
1	+9.420	Berlin has a population of 3,520,031 registered inhabitants in an area of 891.82 km².
2	+1.903	In 2019 the city recorded 3.7 million residents within its metropolitan area.
3	-2.962	Berlin is well known for its museums, its nightlife and its history.
4	-4.419	The capital of France is Paris, a city of about 2.1 million people.
5	-10.972	ベルリンの人口はおよそ350万人です。
6	-11.215	Water boils at 100 degrees Celsius at sea level.

The narrowest gap between adjacent ranks here is 0.2435 logits.

token_type_ids is not optional

A BERT cross-encoder marks the document half of the pair with segment id 1, and the segment embedding is doing real work. Measured on this model with the query above and the passage that answers it, feeding zeros instead of the real segment ids moves the score from +9.42 to +7.83, a drop of 1.59 logits, which leaves the ranking intact here but shifts every score. The graph therefore takes three inputs. XLM-R rerankers (type_vocab_size: 1) have no second segment and take two; the signature follows the model rather than being made uniform.

The attention is eager, and that is the faster export

F.scaled_dot_product_attention does not survive export as one operation. The edge dialect lowers it through _safe_softmax, whose guard against a row with no unmasked key at all leaves 11 operations XNNPACK cannot take, in every attention block — scalar_tensor, where, mul.Scalar, logical_not, eq, full_like, any.dim. Each one cuts the subgraph in two.

The switch is attn_implementation="eager": transformers then builds the mask itself, as torch.finfo(dtype).min, instead of handing F.sdpa a boolean mask for PyTorch to fill with -inf.

The guard is emitted whether or not it can ever fire, and here it cannot: it triggers only on -inf, and this arm never produces one. So the two differ only about rows that have no unmasked key at all — sdpa zeroes them, this one gives them a uniform row — and those are padding rows, which the pooling discards and which every real query row masks out anyway. Measured with all but eight positions masked, as adversarial as this shape gets, the two graphs agree to 1.1e-05.

XNNPACK fp32 goes from 63.6% to 80.0% delegated.

Not shipped

• int8 (dynamic) is not shipped: at 69.7 MB it is larger than the fp16 build's 66.9 MB, and its score error is 0.1073 logits. Dynamic int8 quantizes the linear weights and leaves the token embedding table in fp32, while fp16 halves that table too. The table here is 47 MB of a 134 MB model, and the arithmetic says int8 only comes out smaller when the table is under a third of the weights (45 MB) — measured on ten models on this shelf, the rule called all ten correctly.

Verification

python convert/export_rerank.py ms_marco_minilm_l12
python convert/check_rerank.py ms_marco_minilm_l12 fp32

The check has two halves. One is agreement with the model run in eager, in logits and in ranking order. The other is that the ranking is useful at all: the passage that answers the question has to outscore a passage about the same subject that does not — agreement alone would pass a build that ranked by document length in both arms.

(conversion scripts: executorch-models)