Skip to content

WIP [DeepSeek R1] Add DeepSeekV3 Base + Weight Conversion #2171

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

Open
wants to merge 20 commits into
base: master
Choose a base branch
from
Open

WIP [DeepSeek R1] Add DeepSeekV3 Base + Weight Conversion #2171

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
20 commits
Select commit Hold shift + click to select a range
e275e05
Initial commit
DavidLandup0 Mar 1, 2025
e26a0c0
full port
DavidLandup0 Mar 9, 2025
f0f5c55
Add more complete weight conversion script
DavidLandup0 Mar 27, 2025
ed0bed9
attempt to convert to functional subclassing model
DavidLandup0 Mar 27, 2025
e8fed54
Small fixes
DavidLandup0 May 2, 2025
00554bc
Finish functional subclassing model port
DavidLandup0 May 2, 2025
14882a7
use full args
DavidLandup0 May 2, 2025
5b91b17
Fix top_k usage
DavidLandup0 May 2, 2025
040e833
Move model args to config files
DavidLandup0 May 2, 2025
1c26539
Remove model args dataclasses
DavidLandup0 May 2, 2025
ffc7594
Add note and make test config match embedding dims of full config
DavidLandup0 May 31, 2025
ca96974
fix path
DavidLandup0 May 31, 2025
5c832f2
Remove unnecessary configs, add tokenizer class
DavidLandup0 Jun 22, 2025
2680a94
Add causallm class and causallmpreprocessor
DavidLandup0 Jun 22, 2025
9f117d3
Add tokenizer to conversion script
DavidLandup0 Jun 22, 2025
806b1b0
Add cpu() before numpy()
DavidLandup0 Jun 30, 2025
776d4a7
Run api_gen.sh
DavidLandup0 Jun 30, 2025
3418a12
Switch to full model parts
DavidLandup0 Jun 30, 2025
0cf6058
Remove unnecessary token copy
DavidLandup0 Jun 30, 2025
550f677
Fix 0 prefix
DavidLandup0 Jul 7, 2025
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
16 changes: 8 additions & 8 deletions keras_hub/api/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,12 @@
since your modifications would be overwritten.
"""

from keras_hub.api import layers
from keras_hub.api import metrics
from keras_hub.api import models
from keras_hub.api import samplers
from keras_hub.api import tokenizers
from keras_hub.api import utils
from keras_hub.src.utils.preset_utils import upload_preset
from keras_hub.api import layers as layers
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you rebase the code to latest changes in Keras Hub in master and generate API again, so that it will show only the changes from DeepSeek

from keras_hub.api import metrics as metrics
from keras_hub.api import models as models
from keras_hub.api import samplers as samplers
from keras_hub.api import tokenizers as tokenizers
from keras_hub.api import utils as utils
from keras_hub.src.utils.preset_utils import upload_preset as upload_preset
from keras_hub.src.version_utils import __version__
from keras_hub.src.version_utils import version
from keras_hub.src.version_utils import version as version
120 changes: 81 additions & 39 deletions keras_hub/api/layers/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,74 +4,116 @@
since your modifications would be overwritten.
"""

from keras_hub.src.layers.modeling.alibi_bias import AlibiBias
from keras_hub.src.layers.modeling.anchor_generator import AnchorGenerator
from keras_hub.src.layers.modeling.box_matcher import BoxMatcher
from keras_hub.src.layers.modeling.alibi_bias import AlibiBias as AlibiBias
from keras_hub.src.layers.modeling.anchor_generator import (
AnchorGenerator as AnchorGenerator,
)
from keras_hub.src.layers.modeling.box_matcher import BoxMatcher as BoxMatcher
from keras_hub.src.layers.modeling.cached_multi_head_attention import (
CachedMultiHeadAttention,
CachedMultiHeadAttention as CachedMultiHeadAttention,
)
from keras_hub.src.layers.modeling.f_net_encoder import (
FNetEncoder as FNetEncoder,
)
from keras_hub.src.layers.modeling.masked_lm_head import (
MaskedLMHead as MaskedLMHead,
)
from keras_hub.src.layers.modeling.non_max_supression import (
NonMaxSuppression as NonMaxSuppression,
)
from keras_hub.src.layers.modeling.position_embedding import (
PositionEmbedding as PositionEmbedding,
)
from keras_hub.src.layers.modeling.f_net_encoder import FNetEncoder
from keras_hub.src.layers.modeling.masked_lm_head import MaskedLMHead
from keras_hub.src.layers.modeling.non_max_supression import NonMaxSuppression
from keras_hub.src.layers.modeling.position_embedding import PositionEmbedding
from keras_hub.src.layers.modeling.reversible_embedding import (
ReversibleEmbedding,
ReversibleEmbedding as ReversibleEmbedding,
)
from keras_hub.src.layers.modeling.rms_normalization import (
RMSNormalization as RMSNormalization,
)
from keras_hub.src.layers.modeling.rotary_embedding import (
RotaryEmbedding as RotaryEmbedding,
)
from keras_hub.src.layers.modeling.rms_normalization import RMSNormalization
from keras_hub.src.layers.modeling.rotary_embedding import RotaryEmbedding
from keras_hub.src.layers.modeling.sine_position_encoding import (
SinePositionEncoding,
SinePositionEncoding as SinePositionEncoding,
)
from keras_hub.src.layers.modeling.token_and_position_embedding import (
TokenAndPositionEmbedding,
TokenAndPositionEmbedding as TokenAndPositionEmbedding,
)
from keras_hub.src.layers.modeling.transformer_decoder import (
TransformerDecoder as TransformerDecoder,
)
from keras_hub.src.layers.modeling.transformer_encoder import (
TransformerEncoder as TransformerEncoder,
)
from keras_hub.src.layers.preprocessing.audio_converter import (
AudioConverter as AudioConverter,
)
from keras_hub.src.layers.preprocessing.image_converter import (
ImageConverter as ImageConverter,
)
from keras_hub.src.layers.modeling.transformer_decoder import TransformerDecoder
from keras_hub.src.layers.modeling.transformer_encoder import TransformerEncoder
from keras_hub.src.layers.preprocessing.audio_converter import AudioConverter
from keras_hub.src.layers.preprocessing.image_converter import ImageConverter
from keras_hub.src.layers.preprocessing.masked_lm_mask_generator import (
MaskedLMMaskGenerator,
MaskedLMMaskGenerator as MaskedLMMaskGenerator,
)
from keras_hub.src.layers.preprocessing.multi_segment_packer import (
MultiSegmentPacker,
MultiSegmentPacker as MultiSegmentPacker,
)
from keras_hub.src.layers.preprocessing.random_deletion import (
RandomDeletion as RandomDeletion,
)
from keras_hub.src.layers.preprocessing.random_swap import (
RandomSwap as RandomSwap,
)
from keras_hub.src.layers.preprocessing.start_end_packer import (
StartEndPacker as StartEndPacker,
)
from keras_hub.src.layers.preprocessing.random_deletion import RandomDeletion
from keras_hub.src.layers.preprocessing.random_swap import RandomSwap
from keras_hub.src.layers.preprocessing.start_end_packer import StartEndPacker
from keras_hub.src.models.basnet.basnet_image_converter import (
BASNetImageConverter,
BASNetImageConverter as BASNetImageConverter,
)
from keras_hub.src.models.clip.clip_image_converter import (
CLIPImageConverter as CLIPImageConverter,
)
from keras_hub.src.models.clip.clip_image_converter import CLIPImageConverter
from keras_hub.src.models.deeplab_v3.deeplab_v3_image_converter import (
DeepLabV3ImageConverter,
DeepLabV3ImageConverter as DeepLabV3ImageConverter,
)
from keras_hub.src.models.densenet.densenet_image_converter import (
DenseNetImageConverter,
DenseNetImageConverter as DenseNetImageConverter,
)
from keras_hub.src.models.efficientnet.efficientnet_image_converter import (
EfficientNetImageConverter,
EfficientNetImageConverter as EfficientNetImageConverter,
)
from keras_hub.src.models.mit.mit_image_converter import (
MiTImageConverter as MiTImageConverter,
)
from keras_hub.src.models.mit.mit_image_converter import MiTImageConverter
from keras_hub.src.models.mobilenet.mobilenet_image_converter import (
MobileNetImageConverter,
MobileNetImageConverter as MobileNetImageConverter,
)
from keras_hub.src.models.pali_gemma.pali_gemma_image_converter import (
PaliGemmaImageConverter,
PaliGemmaImageConverter as PaliGemmaImageConverter,
)
from keras_hub.src.models.resnet.resnet_image_converter import (
ResNetImageConverter,
ResNetImageConverter as ResNetImageConverter,
)
from keras_hub.src.models.retinanet.retinanet_image_converter import (
RetinaNetImageConverter,
RetinaNetImageConverter as RetinaNetImageConverter,
)
from keras_hub.src.models.sam.sam_image_converter import (
SAMImageConverter as SAMImageConverter,
)
from keras_hub.src.models.sam.sam_mask_decoder import (
SAMMaskDecoder as SAMMaskDecoder,
)
from keras_hub.src.models.sam.sam_prompt_encoder import (
SAMPromptEncoder as SAMPromptEncoder,
)
from keras_hub.src.models.sam.sam_image_converter import SAMImageConverter
from keras_hub.src.models.sam.sam_mask_decoder import SAMMaskDecoder
from keras_hub.src.models.sam.sam_prompt_encoder import SAMPromptEncoder
from keras_hub.src.models.segformer.segformer_image_converter import (
SegFormerImageConverter,
SegFormerImageConverter as SegFormerImageConverter,
)
from keras_hub.src.models.vgg.vgg_image_converter import (
VGGImageConverter as VGGImageConverter,
)
from keras_hub.src.models.vit.vit_image_converter import (
ViTImageConverter as ViTImageConverter,
)
from keras_hub.src.models.vgg.vgg_image_converter import VGGImageConverter
from keras_hub.src.models.vit.vit_image_converter import ViTImageConverter
from keras_hub.src.models.whisper.whisper_audio_converter import (
WhisperAudioConverter,
WhisperAudioConverter as WhisperAudioConverter,
)
10 changes: 5 additions & 5 deletions keras_hub/api/metrics/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,8 +4,8 @@
since your modifications would be overwritten.
"""

from keras_hub.src.metrics.bleu import Bleu
from keras_hub.src.metrics.edit_distance import EditDistance
from keras_hub.src.metrics.perplexity import Perplexity
from keras_hub.src.metrics.rouge_l import RougeL
from keras_hub.src.metrics.rouge_n import RougeN
from keras_hub.src.metrics.bleu import Bleu as Bleu
from keras_hub.src.metrics.edit_distance import EditDistance as EditDistance
from keras_hub.src.metrics.perplexity import Perplexity as Perplexity
from keras_hub.src.metrics.rouge_l import RougeL as RougeL
from keras_hub.src.metrics.rouge_n import RougeN as RougeN
Loading