fix: stop grouping HF/ModelScope models by repository

A repository is not a model identity: collection repos on Hugging Face
and ModelScope host many unrelated models, which were wrongly shown as
versions of each other.

- Hugging Face models no longer auto-group (the Hub exposes no
  site-native model id)
- ModelScope models group by the site's native published-model id
  (MuseInfo modelVersion.modelId), extracted during enrichment and
  persisted on the sidecar as source_model_id/source_version_id;
  unenriched models stay standalone instead of collapsing a whole repo
  into one group
- TensorArt grouping unchanged (its URL id is already model-level)
- Frontend group-key derivation mirrors the new backend semantics
This commit is contained in:
Will Miao
2026-09-25 23:29:30 +08:00
parent 8a80f82d93
commit c48feeddb6
17 changed files with 357 additions and 78 deletions
+29 -4
View File
@@ -25,7 +25,7 @@ import logging
import os
import re
from dataclasses import dataclass, field
from typing import Any, Dict, Iterable, Optional
from typing import Any, Dict, Iterable, Mapping, Optional
import aiohttp
@@ -123,6 +123,20 @@ class ModelCardContext:
trigger_words: list[str] = field(default_factory=list)
"""Trigger words the site records for the requested model file."""
source_model_id: str = ""
"""Site-native id of the *published model* the requested file belongs to.
Sites whose repository is not a model identity publish a separate,
stable id per model (ModelScope's ``modelVersion.modelId`` — identical
across every version of one published model, different between the
models of a collection repository). It is the version-grouping key,
persisted on the sidecar as ``source_model_id``.
"""
source_version_id: str = ""
"""Site-native id of the published version the requested file belongs to
(ModelScope's ``modelVersion.id``), persisted as ``source_version_id``."""
def is_empty(self) -> bool:
"""Return ``True`` when the site contributed nothing extra."""
@@ -139,6 +153,8 @@ class ModelCardContext:
self.official_tags,
self.example_images,
self.trigger_words,
self.source_model_id,
self.source_version_id,
)
)
@@ -329,11 +345,20 @@ class ModelSource:
return ""
def group_key(self, source_id: str) -> str:
"""Return the version-group key for *source_id*."""
def group_key(self, ref: SourceRef, item: Mapping[str, Any]) -> Optional[str]:
"""Return the version-group key for the model described by *item*.
The default groups by source id (``{prefix}:{owner}/{repo}``), which
is only correct when the source id already identifies a single
published model. Sources whose repository hosts many unrelated
models override this: they either derive the key from a site-native
model identity recorded in *item* (ModelScope's ``source_model_id``)
or return ``None`` when the platform has no reliable model identity
at all (Hugging Face), leaving the model ungrouped.
"""
prefix = GROUP_PREFIXES.get(self.platform, self.platform)
return f"{prefix}:{source_id}"
return f"{prefix}:{ref.source_id}"
async def fetch_model_card(self, source_id: str) -> str:
"""Fetch the raw model card (README) markdown for *source_id*."""