Add pydocstyle to the ruff rules (#52136)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com> Signed-off-by: Harry Mellor <hej.mellor@gmail.com> Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 5
parent
804e5377aa
commit
8c1557a79c
@@ -27,8 +27,7 @@ from .utils import PPMissingLayer, extract_layer_index, maybe_prefix
|
||||
|
||||
|
||||
class MellumAttention(Qwen3MoeAttention):
|
||||
"""
|
||||
Differences from `Qwen3MoeAttention`:
|
||||
"""Differences from `Qwen3MoeAttention`:
|
||||
- Supports `per_layer_sliding_window` for `Attention`.
|
||||
"""
|
||||
|
||||
@@ -122,8 +121,7 @@ class MellumAttention(Qwen3MoeAttention):
|
||||
|
||||
|
||||
class MellumDecoderLayer(Qwen3MoeDecoderLayer):
|
||||
"""
|
||||
Differences from `Qwen3MoeDecoderLayer`:
|
||||
"""Differences from `Qwen3MoeDecoderLayer`:
|
||||
- Supports interleaved SWA and per-layer RoPE scaling.
|
||||
"""
|
||||
|
||||
@@ -185,8 +183,7 @@ class MellumDecoderLayer(Qwen3MoeDecoderLayer):
|
||||
|
||||
@support_torch_compile
|
||||
class MellumModel(Qwen3MoeModel):
|
||||
"""
|
||||
Differences from `Qwen3MoeModel`:
|
||||
"""Differences from `Qwen3MoeModel`:
|
||||
- Uses `MellumDecoderLayer`.
|
||||
"""
|
||||
|
||||
@@ -204,8 +201,7 @@ class MellumModel(Qwen3MoeModel):
|
||||
|
||||
|
||||
class MellumForCausalLM(Qwen3MoeForCausalLM):
|
||||
"""
|
||||
Differences from `Qwen3MoeForCausalLM`:
|
||||
"""Differences from `Qwen3MoeForCausalLM`:
|
||||
- Uses `MellumModel`.
|
||||
"""
|
||||
|
||||
|
||||
Reference in New Issue
Block a user