Delete the previous colab
Browse files- deepseek tflite.ipynb +0 -1
deepseek tflite.ipynb
DELETED
@@ -1 +0,0 @@
|
|
1 |
-
{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"widgets":{"application/vnd.jupyter.widget-state+json":{"2a41ab93236a4787ae3195c0d7fbd78d":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_24fc084df31b4f7784a550f395b30def","IPY_MODEL_f22fc12089474efda78948db831f4017","IPY_MODEL_13d0bece889144b390986c158b2f47bf"],"layout":"IPY_MODEL_d02ce728af4a47e3a9be9624c0804cfd"}},"24fc084df31b4f7784a550f395b30def":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_85f564d90df34cd99e102b733b4600e3","placeholder":"β","style":"IPY_MODEL_e36015e3e93f4e428662b93b143ec330","value":""}},"f22fc12089474efda78948db831f4017":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_6eccd2b8ef254166875ee4a3e89e6013","max":1,"min":0,"orientation":"horizontal","style":"IPY_MODEL_cc2fe94b3b1f4195b9bf72156dd97326","value":0}},"13d0bece889144b390986c158b2f47bf":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_0fecb261f2924ab693a72aace58c65f7","placeholder":"β","style":"IPY_MODEL_1dbcc2e17279417b9033a58e8aaa784d","value":"β0/0β[00:00<?,β?it/s]"}},"d02ce728af4a47e3a9be9624c0804cfd":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"85f564d90df34cd99e102b733b4600e3":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"e36015e3e93f4e428662b93b143ec330":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"6eccd2b8ef254166875ee4a3e89e6013":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":"20px"}},"cc2fe94b3b1f4195b9bf72156dd97326":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"0fecb261f2924ab693a72aace58c65f7":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"1dbcc2e17279417b9033a58e8aaa784d":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"b1574b6dbceb4ff889378b3f71b599c9":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_bb887f04627c48c587ad4460c0bee957","IPY_MODEL_ea27f45d52974b96b937b12a4d176fb2","IPY_MODEL_e09a38dec4774c2d8935a8de1ee350bb"],"layout":"IPY_MODEL_116aac0a6b0844a3ba04758e8e2b97df"}},"bb887f04627c48c587ad4460c0bee957":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_d4ece407b6db4e75ba7b71a68cf5e936","placeholder":"β","style":"IPY_MODEL_3927354600354c819b17a544bbb0c28c","value":"deepseek_q8_seq128_ekv1280.tflite:β100%"}},"ea27f45d52974b96b937b12a4d176fb2":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_0520b79c7aea4b909838d6d1ff1fa5f5","max":1808783640,"min":0,"orientation":"horizontal","style":"IPY_MODEL_7f0b51350282439890a4ff9b4e0b22df","value":1808783640}},"e09a38dec4774c2d8935a8de1ee350bb":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_d164f54bd7c742058e172efc35617cd7","placeholder":"β","style":"IPY_MODEL_13007afa6355400bbc2193e919270594","value":"β1.81G/1.81Gβ[00:43<00:00,β41.6MB/s]"}},"116aac0a6b0844a3ba04758e8e2b97df":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d4ece407b6db4e75ba7b71a68cf5e936":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"3927354600354c819b17a544bbb0c28c":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"0520b79c7aea4b909838d6d1ff1fa5f5":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"7f0b51350282439890a4ff9b4e0b22df":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"d164f54bd7c742058e172efc35617cd7":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"13007afa6355400bbc2193e919270594":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"f7cd9e44a4ce40d8a8374b85359541ba":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_b49a9ab21d5e4bb7801ff59e0c75e7cc","IPY_MODEL_994ae8931c06413482e027954afac240","IPY_MODEL_555968e6925b40fcbecf535d3bac343d"],"layout":"IPY_MODEL_8bba689eeb7d4b1da01f0952261faed3"}},"b49a9ab21d5e4bb7801ff59e0c75e7cc":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_f01be1d3adac4b5684cbcbd9de4f02a9","placeholder":"β","style":"IPY_MODEL_7f16846716074154a2081ec4064a3fd5","value":"tokenizer_config.json:β100%"}},"994ae8931c06413482e027954afac240":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_251cfd83ee72493a8da8ff44e3c88a0f","max":3071,"min":0,"orientation":"horizontal","style":"IPY_MODEL_ab6239b03e4348f48264a80d58ba955c","value":3071}},"555968e6925b40fcbecf535d3bac343d":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_0c7a25e97a7e4cb2972dccdca6535fd7","placeholder":"β","style":"IPY_MODEL_e0b68935d7e84a139b0b87082a84726e","value":"β3.07k/3.07kβ[00:00<00:00,β294kB/s]"}},"8bba689eeb7d4b1da01f0952261faed3":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"f01be1d3adac4b5684cbcbd9de4f02a9":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"7f16846716074154a2081ec4064a3fd5":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"251cfd83ee72493a8da8ff44e3c88a0f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"ab6239b03e4348f48264a80d58ba955c":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"0c7a25e97a7e4cb2972dccdca6535fd7":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"e0b68935d7e84a139b0b87082a84726e":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"dafea85e1ee54880969d463ed2bea3b3":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_fdc2d972cb6f41dd956b3834ff0079d5","IPY_MODEL_178b48ef1cf74945b501e71b87b79aee","IPY_MODEL_6364cb12d75d4cc68fce1c615c2bfe93"],"layout":"IPY_MODEL_9d0110a2c01a4a548166aafe9212f7d7"}},"fdc2d972cb6f41dd956b3834ff0079d5":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_4e0251d51b10442bbe47524367ab8fc1","placeholder":"β","style":"IPY_MODEL_617aa67db0174a1bb5b16c75d710a377","value":"tokenizer.json:β100%"}},"178b48ef1cf74945b501e71b87b79aee":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_de9eb7ed0d5f4b0487034b3a09d505f3","max":7031660,"min":0,"orientation":"horizontal","style":"IPY_MODEL_638da955bce8438d9b6ac0617ca1291f","value":7031660}},"6364cb12d75d4cc68fce1c615c2bfe93":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_0a780da815d348aca88a832aa12be426","placeholder":"β","style":"IPY_MODEL_8e3bd93e9f4243c099f688d78588eceb","value":"β7.03M/7.03Mβ[00:00<00:00,β13.8MB/s]"}},"9d0110a2c01a4a548166aafe9212f7d7":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"4e0251d51b10442bbe47524367ab8fc1":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"617aa67db0174a1bb5b16c75d710a377":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"de9eb7ed0d5f4b0487034b3a09d505f3":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"638da955bce8438d9b6ac0617ca1291f":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"0a780da815d348aca88a832aa12be426":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"8e3bd93e9f4243c099f688d78588eceb":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}}}},"cells":[{"cell_type":"markdown","source":["#Install dependencies"],"metadata":{"id":"39AMoCOa1ckc"}},{"cell_type":"code","source":["!pip install ai-edge-litert-nightly"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"43tAeO0AZ7zp","executionInfo":{"status":"ok","timestamp":1739575672054,"user_tz":480,"elapsed":3026,"user":{"displayName":"Xu Chen","userId":"14086863852433201070"}},"outputId":"c51267ca-7090-4b98-b6cf-4232705dcf93"},"execution_count":3,"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting ai-edge-litert-nightly\n"," Downloading ai_edge_litert_nightly-1.1.2.dev20250213-cp311-cp311-manylinux_2_17_x86_64.whl.metadata (1.6 kB)\n","Requirement already satisfied: flatbuffers in /usr/local/lib/python3.11/dist-packages (from ai-edge-litert-nightly) (25.2.10)\n","Requirement already satisfied: numpy>=1.23.2 in /usr/local/lib/python3.11/dist-packages (from ai-edge-litert-nightly) (1.26.4)\n","Downloading ai_edge_litert_nightly-1.1.2.dev20250213-cp311-cp311-manylinux_2_17_x86_64.whl (3.5 MB)\n","\u001b[2K \u001b[90mββββββββββββββββββββββββββββββββββββββββ\u001b[0m \u001b[32m3.5/3.5 MB\u001b[0m \u001b[31m29.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hInstalling collected packages: ai-edge-litert-nightly\n","Successfully installed ai-edge-litert-nightly-1.1.2.dev20250213\n"]}]},{"cell_type":"code","source":["from ai_edge_litert import interpreter as interpreter_lib\n","from transformers import AutoTokenizer\n","import numpy as np\n","from collections.abc import Sequence\n","import sys"],"metadata":{"id":"i6PMkMVBPr1p","colab":{"base_uri":"https://localhost:8080/","height":86,"referenced_widgets":["2a41ab93236a4787ae3195c0d7fbd78d","24fc084df31b4f7784a550f395b30def","f22fc12089474efda78948db831f4017","13d0bece889144b390986c158b2f47bf","d02ce728af4a47e3a9be9624c0804cfd","85f564d90df34cd99e102b733b4600e3","e36015e3e93f4e428662b93b143ec330","6eccd2b8ef254166875ee4a3e89e6013","cc2fe94b3b1f4195b9bf72156dd97326","0fecb261f2924ab693a72aace58c65f7","1dbcc2e17279417b9033a58e8aaa784d"]},"executionInfo":{"status":"ok","timestamp":1739575692395,"user_tz":480,"elapsed":12314,"user":{"displayName":"Xu Chen","userId":"14086863852433201070"}},"outputId":"b2d7d911-188b-4b9d-d7c9-584bbe617062"},"execution_count":4,"outputs":[{"output_type":"stream","name":"stderr","text":["The cache for model files in Transformers v4.22.0 has been updated. Migrating your old cache. This is a one-time only operation. You can interrupt this and resume the migration later on by calling `transformers.utils.move_cache()`.\n"]},{"output_type":"display_data","data":{"text/plain":["0it [00:00, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"2a41ab93236a4787ae3195c0d7fbd78d"}},"metadata":{}}]},{"cell_type":"markdown","source":["# Download model files"],"metadata":{"id":"K5okZCTgYpUd"}},{"cell_type":"code","source":["from huggingface_hub import hf_hub_download\n","model_path = hf_hub_download(repo_id=\"litert-community/DeepSeek-R1-Distill-Qwen-1.5B\", filename=\"deepseek_q8_seq128_ekv1280.tflite\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":49,"referenced_widgets":["b1574b6dbceb4ff889378b3f71b599c9","bb887f04627c48c587ad4460c0bee957","ea27f45d52974b96b937b12a4d176fb2","e09a38dec4774c2d8935a8de1ee350bb","116aac0a6b0844a3ba04758e8e2b97df","d4ece407b6db4e75ba7b71a68cf5e936","3927354600354c819b17a544bbb0c28c","0520b79c7aea4b909838d6d1ff1fa5f5","7f0b51350282439890a4ff9b4e0b22df","d164f54bd7c742058e172efc35617cd7","13007afa6355400bbc2193e919270594"]},"id":"3t47HAG2tvc3","executionInfo":{"status":"ok","timestamp":1739575646119,"user_tz":480,"elapsed":44372,"user":{"displayName":"Xu Chen","userId":"14086863852433201070"}},"outputId":"26c83638-5caf-4ab0-9466-2cce95bc5966"},"execution_count":1,"outputs":[{"output_type":"display_data","data":{"text/plain":["deepseek_q8_seq128_ekv1280.tflite: 0%| | 0.00/1.81G [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"b1574b6dbceb4ff889378b3f71b599c9"}},"metadata":{}}]},{"cell_type":"markdown","source":["# Create LiteRT interpreter and tokenizer"],"metadata":{"id":"n5Xa4s6XhWqk"}},{"cell_type":"code","source":["interpreter = interpreter_lib.InterpreterWithCustomOps(\n"," custom_op_registerers=[\"pywrap_genai_ops.GenAIOpsRegisterer\"],\n"," model_path=model_path,\n"," num_threads=2,\n"," experimental_default_delegate_latest_features=True)\n","tokenizer = AutoTokenizer.from_pretrained(\"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":81,"referenced_widgets":["f7cd9e44a4ce40d8a8374b85359541ba","b49a9ab21d5e4bb7801ff59e0c75e7cc","994ae8931c06413482e027954afac240","555968e6925b40fcbecf535d3bac343d","8bba689eeb7d4b1da01f0952261faed3","f01be1d3adac4b5684cbcbd9de4f02a9","7f16846716074154a2081ec4064a3fd5","251cfd83ee72493a8da8ff44e3c88a0f","ab6239b03e4348f48264a80d58ba955c","0c7a25e97a7e4cb2972dccdca6535fd7","e0b68935d7e84a139b0b87082a84726e","dafea85e1ee54880969d463ed2bea3b3","fdc2d972cb6f41dd956b3834ff0079d5","178b48ef1cf74945b501e71b87b79aee","6364cb12d75d4cc68fce1c615c2bfe93","9d0110a2c01a4a548166aafe9212f7d7","4e0251d51b10442bbe47524367ab8fc1","617aa67db0174a1bb5b16c75d710a377","de9eb7ed0d5f4b0487034b3a09d505f3","638da955bce8438d9b6ac0617ca1291f","0a780da815d348aca88a832aa12be426","8e3bd93e9f4243c099f688d78588eceb"]},"id":"Rvdn3EIZhaQn","executionInfo":{"status":"ok","timestamp":1739575701096,"user_tz":480,"elapsed":1636,"user":{"displayName":"Xu Chen","userId":"14086863852433201070"}},"outputId":"04422c90-789b-4ea5-a852-a2de9ca666e1"},"execution_count":5,"outputs":[{"output_type":"display_data","data":{"text/plain":["tokenizer_config.json: 0%| | 0.00/3.07k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"f7cd9e44a4ce40d8a8374b85359541ba"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["tokenizer.json: 0%| | 0.00/7.03M [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"dafea85e1ee54880969d463ed2bea3b3"}},"metadata":{}}]},{"cell_type":"markdown","source":["# Create pipeline with LiteRT models"],"metadata":{"id":"AM6rDABTXt2F"}},{"cell_type":"code","source":["\n","class LiteRTLlmPipeline:\n","\n"," def __init__(self, interpreter, tokenizer):\n"," \"\"\"Initializes the pipeline.\"\"\"\n"," self._interpreter = interpreter\n"," self._tokenizer = tokenizer\n","\n"," self._prefill_runner = None\n"," self._decode_runner = self._interpreter.get_signature_runner(\"decode\")\n","\n","\n"," def _init_prefill_runner(self, num_input_tokens: int):\n"," \"\"\"Initializes all the variables related to the prefill runner.\n","\n"," This method initializes the following variables:\n"," - self._prefill_runner: The prefill runner based on the input size.\n"," - self._max_seq_len: The maximum sequence length supported by the model.\n"," - self._max_kv_cache_seq_len: The maximum sequence length supported by the\n"," KV cache.\n"," - self._num_layers: The number of layers in the model.\n","\n"," Args:\n"," num_input_tokens: The number of input tokens.\n"," \"\"\"\n","\n"," self._prefill_runner = self._get_prefill_runner(num_input_tokens)\n"," # input_token_shape has shape (batch, max_seq_len)\n"," input_token_shape = self._prefill_runner.get_input_details()[\"tokens\"][\n"," \"shape\"\n"," ]\n"," if len(input_token_shape) == 1:\n"," self._max_seq_len = input_token_shape[0]\n"," else:\n"," self._max_seq_len = input_token_shape[1]\n","\n"," # kv cache input has shape [batch=1, seq_len, num_heads, dim].\n"," kv_cache_shape = self._prefill_runner.get_input_details()[\"kv_cache_k_0\"][\n"," \"shape\"\n"," ]\n"," self._max_kv_cache_seq_len = kv_cache_shape[1]\n","\n"," # The two arguments excluded are `tokens` and `input_pos`. Dividing by 2\n"," # because each layer has key and value caches.\n"," self._num_layers = (\n"," len(self._prefill_runner.get_input_details().keys()) - 2\n"," ) // 2\n","\n","\n"," def _init_kv_cache(self) -> dict[str, np.ndarray]:\n"," if self._prefill_runner is None:\n"," raise ValueError(\"Prefill runner is not initialized.\")\n"," kv_cache = {}\n"," for i in range(self._num_layers):\n"," kv_cache[f\"kv_cache_k_{i}\"] = np.zeros(\n"," self._prefill_runner.get_input_details()[f\"kv_cache_k_{i}\"][\"shape\"],\n"," dtype=np.float32,\n"," )\n"," kv_cache[f\"kv_cache_v_{i}\"] = np.zeros(\n"," self._prefill_runner.get_input_details()[f\"kv_cache_v_{i}\"][\"shape\"],\n"," dtype=np.float32,\n"," )\n"," return kv_cache\n","\n"," def _get_prefill_runner(self, num_input_tokens: int) :\n"," \"\"\"Gets the prefill runner with the best suitable input size.\n","\n"," Args:\n"," num_input_tokens: The number of input tokens.\n","\n"," Returns:\n"," The prefill runner with the smallest input size.\n"," \"\"\"\n"," best_signature = None\n"," delta = sys.maxsize\n"," max_prefill_len = -1\n"," for key in self._interpreter.get_signature_list().keys():\n"," if \"prefill\" not in key:\n"," continue\n"," input_pos = self._interpreter.get_signature_runner(key).get_input_details()[\n"," \"input_pos\"\n"," ]\n"," # input_pos[\"shape\"] has shape (max_seq_len, )\n"," seq_size = input_pos[\"shape\"][0]\n"," max_prefill_len = max(max_prefill_len, seq_size)\n"," if num_input_tokens <= seq_size and seq_size - num_input_tokens < delta:\n"," delta = seq_size - num_input_tokens\n"," best_signature = key\n"," if best_signature is None:\n"," raise ValueError(\n"," \"The largest prefill length supported is %d, but we have %d number of input tokens\"\n"," %(max_prefill_len, num_input_tokens)\n"," )\n"," return self._interpreter.get_signature_runner(best_signature)\n","\n"," def _greedy_sampler(self, logits: np.ndarray) -> int:\n"," return int(np.argmax(logits))\n","\n"," def generate(self, prompt: str, max_decode_steps: int | None = None) -> str:\n"," messages=[{ 'role': 'user', 'content': prompt}]\n"," token_ids = self._tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True)\n"," # Initialize the prefill runner with the suitable input size.\n"," self._init_prefill_runner(len(token_ids))\n","\n"," actual_max_decode_steps = self._max_kv_cache_seq_len - len(token_ids)\n"," if max_decode_steps is not None:\n"," actual_max_decode_steps = min(actual_max_decode_steps, max_decode_steps)\n","\n"," input_token_ids = [0] * self._max_seq_len\n"," input_token_ids[:len(token_ids)] = token_ids\n"," model_inputs = self._init_kv_cache()\n"," model_inputs.update({\n"," \"tokens\": np.asarray([input_token_ids], dtype=np.int32),\n"," \"input_pos\": np.arange(self._max_seq_len, dtype=np.int32),\n"," })\n"," decode_text = []\n"," decode_step = 0\n"," print('Running prefill')\n"," for step in range(actual_max_decode_steps+1):\n"," signature_runner = self._prefill_runner if step == 0 else self._decode_runner\n"," model_outputs = signature_runner(**model_inputs)\n"," # At prefill stage, output logits has shape (batch=1, seq_size, vocab_size)\n"," # At decode stage, output logits has shape (batch=1, 1, vocab_size).\n"," selected_logit = len(token_ids)-1 if step == 0 else 0\n"," logits = model_outputs.pop(\"logits\")[0][selected_logit]\n","\n"," if step == 0:\n"," print('Running decode')\n","\n"," # Decode text output.\n"," next_token = self._greedy_sampler(logits)\n"," if next_token == self._tokenizer.eos_token_id:\n"," break\n"," decode_text.append(self._tokenizer.decode(next_token, skip_special_tokens=False))\n"," print(decode_text[-1], end='', flush=True)\n"," # The rest of the outputs is the updated kv cache.\n"," model_inputs = model_outputs\n"," model_inputs.update({\n"," \"tokens\": np.array([[next_token]], dtype=np.int32),\n"," \"input_pos\": np.array([decode_step + len(token_ids)], dtype=np.int32),})\n"," decode_step += 1\n","\n","\n","\n"," print() # print a new line at the end.\n"," return ''.join(decode_text)\n"],"metadata":{"id":"UBSGrHrM4ANm","executionInfo":{"status":"ok","timestamp":1739575706507,"user_tz":480,"elapsed":12,"user":{"displayName":"Xu Chen","userId":"14086863852433201070"}}},"execution_count":6,"outputs":[]},{"cell_type":"markdown","source":["# Generate text from model"],"metadata":{"id":"dASKx_JtYXwe"}},{"cell_type":"code","source":["pipeline = LiteRTLlmPipeline(interpreter, tokenizer)"],"metadata":{"id":"AZhlDQWg61AL","executionInfo":{"status":"ok","timestamp":1739575712587,"user_tz":480,"elapsed":4,"user":{"displayName":"Xu Chen","userId":"14086863852433201070"}}},"execution_count":7,"outputs":[]},{"cell_type":"code","source":["prompt = \"What is the capital of France?\"\n","output = pipeline.generate(prompt, max_decode_steps = 20)"],"metadata":{"id":"wT9BIiATkjzL","colab":{"base_uri":"https://localhost:8080/"},"outputId":"e9ee578b-af27-4384-8750-e1de2bd1a5da","executionInfo":{"status":"ok","timestamp":1739576026998,"user_tz":480,"elapsed":8486,"user":{"displayName":"Xu Chen","userId":"14086863852433201070"}}},"execution_count":9,"outputs":[{"output_type":"stream","name":"stdout","text":["Running prefill\n","Running decode\n","Okay, so I need to figure out the capital of France. I remember that France is a country in\n"]}]},{"cell_type":"code","source":[],"metadata":{"id":"GNzDBxDFEuAJ"},"execution_count":null,"outputs":[]}]}
|
|
|
|