Instructions to use DarrenJiaImbue/gemma-4-e4b-it-bouncer-litertlm with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use DarrenJiaImbue/gemma-4-e4b-it-bouncer-litertlm with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli litert-lm run \ --from-huggingface-repo=DarrenJiaImbue/gemma-4-e4b-it-bouncer-litertlm \ model.litertlm \ --prompt="Write me a poem"
- Notebooks
- Google Colab
- Kaggle
Dual-signature export v5: fixed Gemma4 patch registration (gemma4_text was missing), restoring the LiteRT Gemma4RMSNorm forward that emits odml.rms_norm STABLEHLO_COMPOSITE markers. Result: 980 rms_norm composite subgraphs in the prefill-decode tflite, matching upstream Gemma. iOS Metal fused-attention shader should now pattern-match the chat graph.
99cb892 verified - Xet hash:
- cae00a02a01503b61a02c7f3c940e6c47421a3fb71156a39ae685751f1d97ed3
- Size of remote file:
- 4.19 GB
- SHA256:
- f58a1adf8571ac362342c2fb72cb89f0b72427a722fec58a5efe0569ebcff252
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.