| """Configuration class for binomial-shannon-2 (router + ticker + macro). |
| |
| Ships with the model on HuggingFace Hub so |
| `AutoConfig.from_pretrained(repo, trust_remote_code=True)` works. |
| """ |
|
|
| from __future__ import annotations |
|
|
| from transformers.configuration_utils import PretrainedConfig |
|
|
|
|
| |
| EVENTS = ( |
| "earnings", "guidance", "m_and_a", "regulatory_legal", "product", |
| "exec_change", "dividend_buyback", "analyst_rating", "macro_sector", "other", |
| ) |
| CLAIM_TYPES = ("fact", "opinion", "rumor", "forecast") |
|
|
| |
| TOPICS = ( |
| "monetary_policy", "fiscal_policy", "inflation", "growth", "labor", |
| "rates_fixed_income", "equities_markets", "fx_currency", "energy", |
| "commodities", "credit_banking", "crypto", "mergers_acquisitions", |
| "trade_policy", "geopolitics", "single_company", "technicals", "other", |
| ) |
| SEVERITY_BUCKETS = ("noise", "minor", "notable", "major", "crisis") |
| NOVELTY_BUCKETS_MACRO = ("rehash", "commentary", "breaking") |
| CLAIM_TYPES_MACRO = ("fact", "opinion", "rumor", "forecast") |
| HAWKISH_DOVISH_BUCKETS = ( |
| "dovish", "mildly_dovish", "neutral", "mildly_hawkish", "hawkish", |
| ) |
|
|
|
|
| class Shannon2Config(PretrainedConfig): |
| """Config for Shannon2MultiHead. |
| |
| Shared encoder + 2-way router + ticker head bank (19 outputs, inherited |
| from shannon-1) + macro head bank (35 outputs). Mirrors shannon-1's hub |
| configuration approach. |
| """ |
|
|
| model_type = "shannon2" |
|
|
| def __init__( |
| self, |
| encoder_name_or_path: str = "answerdotai/ModernBERT-base", |
| max_position_embeddings: int = 4096, |
| head_h1: int = 512, |
| head_h2: int = 256, |
| dropout: float = 0.1, |
| events: tuple[str, ...] = EVENTS, |
| claim_types: tuple[str, ...] = CLAIM_TYPES, |
| topics: tuple[str, ...] = TOPICS, |
| severity_buckets: tuple[str, ...] = SEVERITY_BUCKETS, |
| novelty_buckets_macro: tuple[str, ...] = NOVELTY_BUCKETS_MACRO, |
| claim_types_macro: tuple[str, ...] = CLAIM_TYPES_MACRO, |
| hawkish_dovish_buckets: tuple[str, ...] = HAWKISH_DOVISH_BUCKETS, |
| **kwargs, |
| ) -> None: |
| super().__init__(**kwargs) |
| self.encoder_name_or_path = encoder_name_or_path |
| self.max_position_embeddings = max_position_embeddings |
| self.head_h1 = head_h1 |
| self.head_h2 = head_h2 |
| self.dropout = dropout |
| self.events = list(events) |
| self.claim_types = list(claim_types) |
| self.topics = list(topics) |
| self.severity_buckets = list(severity_buckets) |
| self.novelty_buckets_macro = list(novelty_buckets_macro) |
| self.claim_types_macro = list(claim_types_macro) |
| self.hawkish_dovish_buckets = list(hawkish_dovish_buckets) |
|
|
