Prep for 0.3.5 release
ANEMLL: Open Source project (pronounced as animal) PRO
anemll
AI & ML interests
Apple Neural Engine, on-device-compute
Recent Activity
updated
a collection
about 1 hour ago
Anemll-chat
updated
a collection
2 days ago
Anemll-chat
updated
a collection
2 days ago
Anemll-chat
Organizations
ANEMLL-0.3.4
Models build with 0.3.4, improved quality and bug fixes
Papers to review
Just an EZ way to collect papers on HF
-
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 33 -
TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation
Paper • 2503.04872 • Published • 15 -
FFN Fusion: Rethinking Sequential Computation in Large Language Models
Paper • 2503.18908 • Published • 19
ANEML 0.1.2
conversions done with 0.1.2
Google Gemma-3 for ANE
ANEMLL conversion of Google's models
-
anemll/anemll-google-gemma-3-1b-it-ctx4096_0.3.4
Updated • 66 • 1 -
anemll/anemll-google-gemma-3-4b-it-qat-int4-unquantized-ctx1024_0.3.5
Updated • 29 -
anemll/anemll-google-gemma-3-4b-it-qat-int4-unquantized-ctx4096_0.3.5
Updated • 40 -
anemll/anemll-google-gemma-3-270m-it-ctx512-monolithic_0.3.5
Updated • 46
Qwen3 for ANE
Initial Support for QWEN3
ANEMLL iOS
Unzipped models for iOS downloads, test only
ANEMLL-0.1.1
Models converted with ANEMLL - 0.1.11 and one shot convert script https://github.com/Anemll/Anemll/blob/main/docs/convert_model.md
Anemll-chat
Prep for 0.3.5 release
Google Gemma-3 for ANE
ANEMLL conversion of Google's models
-
anemll/anemll-google-gemma-3-1b-it-ctx4096_0.3.4
Updated • 66 • 1 -
anemll/anemll-google-gemma-3-4b-it-qat-int4-unquantized-ctx1024_0.3.5
Updated • 29 -
anemll/anemll-google-gemma-3-4b-it-qat-int4-unquantized-ctx4096_0.3.5
Updated • 40 -
anemll/anemll-google-gemma-3-270m-it-ctx512-monolithic_0.3.5
Updated • 46
ANEMLL-0.3.4
Models build with 0.3.4, improved quality and bug fixes
Qwen3 for ANE
Initial Support for QWEN3
Papers to review
Just an EZ way to collect papers on HF
-
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
Paper • 2405.12981 • Published • 33 -
TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation
Paper • 2503.04872 • Published • 15 -
FFN Fusion: Rethinking Sequential Computation in Large Language Models
Paper • 2503.18908 • Published • 19
ANEMLL iOS
Unzipped models for iOS downloads, test only
ANEML 0.1.2
conversions done with 0.1.2
ANEMLL-0.1.1
Models converted with ANEMLL - 0.1.11 and one shot convert script https://github.com/Anemll/Anemll/blob/main/docs/convert_model.md