REAX SN92 generalist entry
Decision model for the REAX (SN92) generalist track, served with the validator's fixed prompt and joint letter readout (softmax at T=2).
Lineage and modifications
Qwen/Qwen3.5-27B (Apache-2.0) -> baselabs/mammoth-1@61cec44c281c693992e3d6ebeb44dd3402dfa186 (MIT; a full fine-tune for decisions by Base Labs, Baseten) -> rewritten to the joint readout layout (Qwen3_5Model backbone, all tensors unchanged and renamed; the untied LM head dropped; readout rows = 2 x the LM-head rows of the answer-code tokens; decision_config v2) -> a NEW LoRA r32 (alpha 64, all linear layers of the language model; the vision tower untouched) trained in joint mode (bidirectional full attention over the prompt, as the REAX validator serves it) for 1500 steps of 32 rows (lr 2.5e-5, cosine schedule) with the answer-letter readout rows A..Z, on decision items in the eval v5.1 item format (procedural generators with exact solvers and rule engines, records from public sources, public benchmark TRAIN splits and our own written items, fact questions about facts dated on or after 1 August 2026 whose target is "I don't know", next to answerable questions about older facts) plus a replay of public SN92 specialist train / factory rows (decisionmodels/sn92-specialists, CC-BY-4.0) and procedural TRAIN rows (tasksource/procedural-typed-decisions, Apache-2.0); merged into the backbone; readout rows A..Z rescaled by the fitted alpha (2.7), then shifted by the mean of rows A and B ((w_A+w_B)/2 subtracted from every row A..Z: a common shift that leaves the option softmax unchanged) for the fixed T=2 readout. Data sources (source id, collection dates): amazon_massive_1_1_en_us_cc_by_4 (2026-10-23); artic_api_cc0_description_cc_by_4 (2026-10-24); arxiv_api_metadata_cc0 (2026-10-23); cpsc_saferproducts_recalls_public_domain (2026-10-24); eurlex_cellar_sparql_eu_reuse (2026-10-24); federal_register_api_public_domain (2026-10-23); github_advisory_database_cc_by_4 (2026-10-23, 2026-10-25); legislation_gov_uk_feeds_ogl_v3 (2026-10-24); met_open_access_csv_cc0 (2026-10-24); msha_open_government_accidents_public_domain (2026-10-24); nasa_image_video_library_api (2026-10-24); nasa_ntrs_api_public_use (2026-10-24); nih_reporter_api_v2_public (2026-10-24); nist_nvd_cve_api_2_public_domain (2026-10-24); noaa_ncei_storm_events_public_domain (2026-10-24); nsf_award_api_public (2026-10-24); open_canada_ca_ckan_ogl_canada_2 (2026-10-24); openalex_works_cc0 (2026-10-23); openfda_enforcement_cc0 (2026-10-23); osha_severe_injury_reports_public_domain (2026-10-24); procedural_random_playout_stockfish16_gold_train (2026-10-23); procgen_arithmetic_train (2026-10-23); procgen_benefit_rules_train (2026-10-23); procgen_bonus_tier_v84 (2026-10-24); procgen_building_permit_fee_v84 (2026-10-25); procgen_bulk_pricing_v84 (2026-10-25); procgen_bulky_waste_v84 (2026-10-25); procgen_c4_v86 (2026-10-25); procgen_causal_train (2026-10-23); procgen_chess_v86 (2026-10-25); procgen_childcare_subsidy_v84 (2026-10-25); procgen_connect4_exact_solver_train (2026-10-24); procgen_coupon_stacking_v84 (2026-10-25); procgen_data_retention_v84 (2026-10-25); procgen_flyer_status_v84 (2026-10-25); procgen_insurance_payout_v82 (2026-10-24); procgen_jury_deferral_v84 (2026-10-25); procgen_kqk_krk_retrograde_dtm_train (2026-10-24); procgen_leave_carryover_v84 (2026-10-24); procgen_library_fine_v84 (2026-10-25); procgen_loan_approval_v82 (2026-10-24); procgen_logic_train (2026-10-23); procgen_loyalty_tier_v84 (2026-10-25); procgen_meeting_scheduler_train (2026-10-23); procgen_nim_family_exhaustive_search_train (2026-10-24); procgen_nim_v86 (2026-10-25); procgen_overtime_pay_v82 (2026-10-24); procgen_parking_tariff_train (2026-10-23); procgen_per_diem_v84 (2026-10-24); procgen_pharmacy_refill_v82 (2026-10-24); procgen_price_match_v84 (2026-10-25); procgen_probability_train (2026-10-23); procgen_python_code_train (2026-10-23); procgen_remote_stipend_v84 (2026-10-24); procgen_return_policy_train (2026-10-23); procgen_sick_note_v84 (2026-10-24); procgen_sla_credit_v84 (2026-10-25); procgen_sql_sqlite_train (2026-10-23); procgen_subscription_refund_v84 (2026-10-25); procgen_tax_schedule_train (2026-10-23); procgen_tictactoe_minimax_train (2026-10-23); procgen_toll_charge_v84 (2026-10-25); procgen_ttt_v86 (2026-10-25); procgen_utility_bill_v82 (2026-10-24); procgen_warranty_claim_v82 (2026-10-24); project_gutenberg_catalog_cc0 (2026-10-24); realapi_box_openapi_apache2 (2026-10-23); realapi_github_rest_mit (2026-10-23); realapi_kubernetes_openapi_apache2 (2026-10-23); realapi_stripe_openapi_mit (2026-10-23); realapi_twilio_api_v2010_mit (2026-10-23); stackexchange_api_cc_by_sa_4 (2026-10-24); ted_eu_tenders_reuse_decision_2011_833_eu (2026-10-23, 2026-10-24, 2026-10-25); trgen_fictional_api_v1 (2026-10-23); uk_parliament_written_questions_api_open_parliament_licence (2026-10-24); usda_fooddata_central_branded_cc0 (2026-10-24); usgs_pubs_warehouse_numbered_series_public_domain (2026-10-24); wikidata_cc0_qlever_train (2026-10-23, 2026-10-25); wikipedia_en_afd_cc_by_sa_4 (2026-10-23); wikipedia_en_requested_moves_cc_by_sa_4 (2026-10-24); wikipedia_en_requests_for_adminship_cc_by_sa_4 (2026-10-24); wikipedia_en_xfd_cc_by_sa_4 (2026-10-25).
Declared base for the track: baselabs/mammoth-1@61cec44c281c693992e3d6ebeb44dd3402dfa186. Weights only; no code. Licence: MIT (see LICENSE and NOTICE; the base of mammoth-1, Qwen/Qwen3.5-27B, is Apache-2.0).
Not affiliated with, endorsed by, or sponsored by Base Labs / Baseten or the Qwen team.
- Downloads last month
- 86