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

*Mac arm64, single process, median of 10, one query-document pair at 512 tokens — a reference point for relative cost, not a device number. PyTorch eager fp32 on the same machine: 26.7 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?"

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.

Not shipped

• int8 (dynamic) is not shipped : at 69.7 MB it is larger than the fp16 build's 67.0 MB, and its score error is 0.1148 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 )