feat: add failure-aware preflight and Qwen review
This commit is contained in:
CoolBoy
@@ -2,6 +2,8 @@ from __future__ import annotations
|
||||
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime
|
||||
from pathlib import PurePosixPath
|
||||
from typing import Any
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -33,10 +35,148 @@ class HFModelSummary:
|
||||
class ModelInspection:
|
||||
repo_id: str
|
||||
file_paths: list[str] = field(default_factory=list)
|
||||
file_sizes: dict[str, int] = field(default_factory=dict)
|
||||
gguf_files: list[str] = field(default_factory=list)
|
||||
selected_gguf: str | None = None
|
||||
weight_files: list[str] = field(default_factory=list)
|
||||
onnx_files: list[str] = field(default_factory=list)
|
||||
model_config: dict[str, Any] = field(default_factory=dict)
|
||||
config_fetch_error: str | None = None
|
||||
|
||||
@property
|
||||
def root_file_names(self) -> set[str]:
|
||||
return {
|
||||
PurePosixPath(path).name.lower()
|
||||
for path in self.file_paths
|
||||
if len(PurePosixPath(path).parts) == 1
|
||||
}
|
||||
|
||||
@property
|
||||
def has_root_config(self) -> bool:
|
||||
return "config.json" in self.root_file_names
|
||||
|
||||
@property
|
||||
def has_root_tokenizer(self) -> bool:
|
||||
names = self.root_file_names
|
||||
exact_names = {
|
||||
"tokenizer.json",
|
||||
"tokenizer_config.json",
|
||||
"tokenizer.model",
|
||||
"sentencepiece.bpe.model",
|
||||
"sentencepiece.model",
|
||||
"spiece.model",
|
||||
"vocab.json",
|
||||
"vocab.txt",
|
||||
}
|
||||
return bool(names & exact_names) or any(
|
||||
name.startswith(("tokenizer_", "tokenization_")) and name.endswith(".py")
|
||||
for name in names
|
||||
)
|
||||
|
||||
@property
|
||||
def has_root_standard_weights(self) -> bool:
|
||||
direct = any(
|
||||
len(PurePosixPath(path).parts) == 1
|
||||
for path in [*self.weight_files, *self.onnx_files]
|
||||
)
|
||||
if direct:
|
||||
return True
|
||||
names = self.root_file_names
|
||||
has_index = any(
|
||||
name.endswith((".safetensors.index.json", ".bin.index.json"))
|
||||
for name in names
|
||||
)
|
||||
return has_index and bool(self.weight_files or self.onnx_files)
|
||||
|
||||
@property
|
||||
def model_type(self) -> str | None:
|
||||
value = self.model_config.get("model_type")
|
||||
return str(value).strip() if value not in (None, "") else None
|
||||
|
||||
@property
|
||||
def architectures(self) -> list[str]:
|
||||
value = self.model_config.get("architectures")
|
||||
if isinstance(value, list):
|
||||
return [str(item).strip() for item in value if str(item).strip()]
|
||||
if value not in (None, ""):
|
||||
return [str(value).strip()]
|
||||
return []
|
||||
|
||||
@property
|
||||
def quantization_method(self) -> str | None:
|
||||
value = self.model_config.get("quantization_config")
|
||||
if isinstance(value, dict):
|
||||
method = value.get("quant_method") or value.get("quantization_method")
|
||||
if method not in (None, ""):
|
||||
return str(method).strip().lower()
|
||||
return None
|
||||
|
||||
@property
|
||||
def max_context_length(self) -> int | None:
|
||||
for key in (
|
||||
"max_position_embeddings",
|
||||
"model_max_length",
|
||||
"seq_length",
|
||||
"n_positions",
|
||||
"max_seq_len",
|
||||
):
|
||||
value = self.model_config.get(key)
|
||||
try:
|
||||
parsed = int(value)
|
||||
except (TypeError, ValueError):
|
||||
continue
|
||||
if 0 < parsed <= 10_000_000:
|
||||
return parsed
|
||||
return None
|
||||
|
||||
@property
|
||||
def repository_size_bytes(self) -> int | None:
|
||||
"""Return exact recursive on-disk size when every file has a size."""
|
||||
if not self.file_paths or any(path not in self.file_sizes for path in self.file_paths):
|
||||
return None
|
||||
total = sum(max(0, int(self.file_sizes[path])) for path in self.file_paths)
|
||||
return total if total > 0 else None
|
||||
|
||||
def estimated_load_bytes(self, framework: str) -> int | None:
|
||||
if framework == "llamacpp":
|
||||
if not self.selected_gguf:
|
||||
return None
|
||||
for path in self.gguf_files:
|
||||
if PurePosixPath(path).name == self.selected_gguf:
|
||||
size = int(self.file_sizes.get(path) or 0)
|
||||
return size or None
|
||||
return None
|
||||
|
||||
if "onnx" in framework or "sherpa" in framework:
|
||||
sizes = [
|
||||
int(self.file_sizes.get(path) or 0)
|
||||
for path in self.onnx_files
|
||||
if len(PurePosixPath(path).parts) == 1
|
||||
]
|
||||
total = sum(size for size in sizes if size > 0)
|
||||
return total or None
|
||||
|
||||
# Repositories occasionally publish both .bin and .safetensors copies.
|
||||
# The runtime loads one complete format, so use the smallest positive
|
||||
# root-level format total instead of double-counting alternatives.
|
||||
root_names = self.root_file_names
|
||||
has_root_index = any(
|
||||
name.endswith((".safetensors.index.json", ".bin.index.json"))
|
||||
for name in root_names
|
||||
)
|
||||
totals: dict[str, int] = {}
|
||||
for path in self.weight_files:
|
||||
# A root index may legally reference shards in subdirectories. In
|
||||
# that case include every shard of each format so large indexed
|
||||
# checkpoints cannot evade the preflight size calculation.
|
||||
if not has_root_index and len(PurePosixPath(path).parts) != 1:
|
||||
continue
|
||||
suffix = PurePosixPath(path).suffix.lower()
|
||||
size = int(self.file_sizes.get(path) or 0)
|
||||
if size > 0:
|
||||
totals[suffix] = totals.get(suffix, 0) + size
|
||||
positive = [value for value in totals.values() if value > 0]
|
||||
return min(positive) if positive else None
|
||||
|
||||
@property
|
||||
def has_gguf(self) -> bool:
|
||||
@@ -71,3 +211,4 @@ class CandidateModel:
|
||||
gguf_filename: str | None = None
|
||||
score: float = 0.0
|
||||
warnings: list[str] = field(default_factory=list)
|
||||
preflight_metadata: dict[str, Any] = field(default_factory=dict)
|
||||
|
||||
Reference in New Issue
Block a user