Skip to content

[Bugfix] Fix sliding window in cohere2 model #11358

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 3 commits into from
Closed

[Bugfix] Fix sliding window in cohere2 model #11358

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e2fa044
add cohere2 model
CXIAAAAA Dec 20, 2024
a0cf8b5
fix sliding window
CXIAAAAA Dec 20, 2024
d0bfaa7
linter
CXIAAAAA Dec 20, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion vllm/model_executor/models/commandr.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@

# This file is based on the LLama model definition file in transformers
"""PyTorch Cohere model."""
import copy
from typing import Iterable, List, Optional, Set, Tuple, Union

import torch
Expand Down Expand Up @@ -183,14 +184,15 @@ def __init__(

self.sliding_window = (sliding_window
if layer_has_sliding_window else None)
cache_config = copy.deepcopy(cache_config)
cache_config.sliding_window = self.sliding_window

self.attn = Attention(self.num_heads,
self.head_dim,
self.scaling,
num_kv_heads=self.num_kv_heads,
cache_config=cache_config,
quant_config=quant_config,
per_layer_sliding_window=self.sliding_window,
prefix=f"{prefix}.attn")
if self.use_qk_norm:
self.q_norm = LayerNorm(param_shape=(self.num_heads,
Expand Down
Loading