Skip to content
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.

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

remove incorrect urls pointing to the llava repository #31107

Merged
merged 5 commits into from
Jul 2, 2024
Merged
Show file tree
Hide file tree
Changes from 3 commits
Commits
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
3 changes: 0 additions & 3 deletions src/transformers/models/idefics2/modeling_idefics2.py
Original file line number Diff line number Diff line change
Expand Up @@ -1344,9 +1344,6 @@ class Idefics2PreTrainedModel(PreTrainedModel):
_supports_cache_class = True

def _init_weights(self, module):
# important: this ported version of Idefics2 isn't meant for training from scratch - only
# inference and fine-tuning - so the proper init weights code has been removed - the original codebase
# https://github.com/haotian-liu/LLaVA/tree/main/idefics2 should serve for that purpose
std = (
self.config.text_config.initializer_range
if hasattr(self.config, "initializer_range")
Expand Down
3 changes: 0 additions & 3 deletions src/transformers/models/llava_next/modeling_llava_next.py
Original file line number Diff line number Diff line change
Expand Up @@ -234,9 +234,6 @@ class LlavaNextPreTrainedModel(PreTrainedModel):
_supports_flash_attn_2 = True

def _init_weights(self, module):
# important: this ported version of LlavaNext isn't meant for training from scratch - only
# inference and fine-tuning - so the proper init weights code has been removed - the original codebase
# https://github.com/haotian-liu/LLaVA/tree/main/llava_next should serve for that purpose
std = (
self.config.initializer_range
if hasattr(self.config, "initializer_range")
Expand Down
3 changes: 0 additions & 3 deletions src/transformers/models/video_llava/modeling_video_llava.py
Original file line number Diff line number Diff line change
Expand Up @@ -129,9 +129,6 @@ class VideoLlavaPreTrainedModel(PreTrainedModel):
_no_split_modules = ["VideoLlavaVisionAttention"]

def _init_weights(self, module):
# important: this ported version of VideoLlava isn't meant for training from scratch - only
# inference and fine-tuning - so the proper init weights code has been removed - the original codebase
# https://github.com/haotian-liu/LLaVA/tree/main/video_llava should serve for that purpose
std = (
self.config.initializer_range
if hasattr(self.config, "initializer_range")
Expand Down
3 changes: 0 additions & 3 deletions src/transformers/models/vipllava/modeling_vipllava.py
Original file line number Diff line number Diff line change
Expand Up @@ -137,9 +137,6 @@ class VipLlavaPreTrainedModel(PreTrainedModel):
_supports_flash_attn_2 = True

def _init_weights(self, module):
# important: this ported version of VipLlava isn't meant for training from scratch - only
# inference and fine-tuning - so the proper init weights code has been removed - the original codebase
# https://github.com/haotian-liu/LLaVA/tree/main/vipllava should serve for that purpose
std = (
self.config.initializer_range
if hasattr(self.config, "initializer_range")
Expand Down