youdotcom/reflex-search (v0.3.3)
Initial public release (v0.3.3) of reflex-search β a compact, CPU-native System 1 search decision and source-ranking model built on the text encoder of google/embeddinggemma-2 (d = 768, 24 text layers with hybrid 512-token sliding and global full attention). Vision and audio towers are removed so the text-only bf16 checkpoint occupies 517 MB on disk and runs in ~196 MB RSS (int8) / ~315 MB RSS (bf16) on commodity CPUs via s1_eg2cpu (adapted from undrgrnd-labs/hunch/eg2cpu).
It powers the reflex-search and reflex-extract MCP tools (/mcp/reflex):
- Gate 1 (Sub-query preflight): Scores parallel candidate sub-queries (
noul_query_matches_intent,choice_best_query_for_intent) to filter off-topic hallucinations and rank over-budget queries before spending Search API calls. - Gate 2 (Unified SERP + Knowledge ranking & routing): Scores web highlights and licensed knowledge facts (
attribution+as_of) on one unified relevance scale (choice_best_search_hit+score_return_relevance), estimates counterfactual full-page read gain (noul_hit_worth_reading), and scores set-level coverage (score_evidence_coverage+choice_next_stepin{answer, read, revise, stop}). - Parallel Extract Intent Scoring: Scores BM25-windowed webpage and PDF passages against caller-supplied
document_intent(score_extract_relevanceondoc_kind = "extracted_doc").
Architecture & Artifact Layout
| File | Format | Size | Contents |
|---|---|---|---|
model.safetensors |
BF16 |
517 MB |
Frozen text-only google/embeddinggemma-2 weights (language_model.*; zero vision/audio weights) |
heads.safetensors |
F32 |
58 MB |
Rank-16 LoRA (layers [17, 20, 21, 22, 23] + embedding_projection, bypassed during prompt embedding for 0.0 retrieval drift) + ChoiceHead, NoulHead, and ScoreHead |
heads.json |
JSON | 9.8 KB |
Head dimensions, query templates, LoRA metadata, and post-hoc (T, b) calibration tables |
calibration.json |
JSON | 2.6 KB |
Single-shot untouched bar_locked holdout seal |
tokenizer.json |
JSON | 31 MB |
Gemma fast BPE tokenizer |
config.json |
JSON | 5.0 KB |
Backbone text configuration |
Untouched Holdout Calibration (bar_locked, 6,155 Rows)
Trained and calibrated on leak-free search and counterfactual multi-rollout trajectories (0 root or query overlap with bar_locked and downstream evaluation benchmarks):
| Cell | Holdout Rows | Proper Loss (vs. Base Rate) | Accuracy / Conditional RPS | Quantile ECE (Gate <= 0.045) |
Perturbation JS (Gate <= 0.005) |
|---|---|---|---|---|---|
Choice:text |
2,024 |
0.1250 < 0.1599 |
49.2% (5-way) |
0.0307 |
0.00079 |
Noul:text |
2,040 |
0.1564 < 0.2500 |
77.5% |
0.0315 |
0.00130 |
Score:text |
2,091 |
0.1185 < 0.3340 |
RPS 0.1554 < 0.2004 |
0.0166 |
0.00130 |
| Combined | 6,155 |
All 3/3 Heads Admitted |
β | 0.0262 <= 0.040 |
0.00113 <= 0.005 |
License & Attribution
- Base weights (
model.safetensors,tokenizer.json,config.json) derive fromgoogle/embeddinggemma-2under the Apache-2.0 license. - LoRA adapters, calibrated RLCD projection heads, and configuration metadata are released under Apache-2.0.
- Downloads last month
- -
Model tree for youdotcom/reflex-search
Base model
google/embeddinggemma-2