nanotron/__init__.py,sha256=sXLh7g3KC4QCFxcZGBTpG2scR7hmmBsMjq6LqRptkRg,22
nanotron/constants.py,sha256=DB5cO2VtO5isOZ3aE7m4ilF3Vc-U-3YhDTYRduvBMbs,146
nanotron/dataloader.py,sha256=PYDqHm8eEX-cIoHGcKpHVQiJiQlRqblvG23lm-w8fyc,22431
nanotron/distributed.py,sha256=Qtdm5f0Bo2qBd_cVGilXHZ1vJqC-8bpgVmHKknB4ySs,10348
nanotron/helpers.py,sha256=_g_Ep5ZGSibUjYTwUWoJcKhAzZy3mWV5jtgbzcJLhSY,20156
nanotron/logging.py,sha256=XrxbEtgZMV0jYGW_bDwnJZhWcWRz0GVR_MHQK7u7aHc,9064
nanotron/random.py,sha256=dOJ0yGmB3BiY3cHDQDul7W8e7QT4zceolocOya7XC78,4700
nanotron/sanity_checks.py,sha256=hZPZ-zmByj7x5C2OJ10Zd6hqWGXoPxWubpURV_ztP5E,9846
nanotron/trainer.py,sha256=7ELjixxhqdEFVhmUJmwos_gPZwp-e45NK4MG96ldQOY,36859
nanotron/utils.py,sha256=Eq2Qt3r7ycOzWjNp6pCbOuT53mlVCTqrr-wdbyHpffk,5361
nanotron/config/__init__.py,sha256=Xhj3aLhAazqW0vr3Ve7p7tcVXl4A09Zm-Nf8aPwu7TA,186
nanotron/config/config.py,sha256=w35pz1hDQZVGLPHaCSrBIQXHbQtfYUwYLNRKMAFrGFQ,13936
nanotron/config/lighteval_config.py,sha256=BCwDpDucUs-rMFTT5g2MnAyXdQtOfKjCmKIqc7q5W8w,2933
nanotron/config/models_config.py,sha256=OoyDkF5mYTdmtsXBmBUYkOdjEq8ex-nmPK1SjXPfujc,3543
nanotron/config/parallelism_config.py,sha256=mPZL-YiFM_YgQ6aVnIDXVGSVhXETXkp3E5X2VtoSOE8,1967
nanotron/config/utils_config.py,sha256=R0L0tiyJuoKnKY7ojh2Bv6DP2rQyjyuvQH4kYiMoVj4,3612
nanotron/generation/__init__.py,sha256=OarEPG2G_RDEsgepHESjnCEnXNm9LwBlnsCI4KzO1cA,198
nanotron/generation/decode.py,sha256=rvxYW8X88-KsRBnRjGdRHM-kYPsu0YQTNjMBN_H8Y_E,40888
nanotron/generation/generate_store.py,sha256=liHDVxfr_aiIDC0tEhs1torP2DXLIL_DjY5ADSXBxJc,1550
nanotron/generation/sampler.py,sha256=wVKRWEnXEwI8cj7VwlmROcVwzfJOinGff3IkqyJ--g0,13758
nanotron/models/__init__.py,sha256=EDAZQjt3yp1aYMV7c25VyuelEvQp-1wiB1xT6oFAj04,130
nanotron/models/base.py,sha256=EjcxPSpVr7F4TfPiurekoirx7vxY6G4uvB1HIam54bk,10327
nanotron/models/llama.py,sha256=79trrUFoaPTvERrBNy-b3q8wsRkhgksvrhfG1XyZYbE,50682
nanotron/models/starcoder2.py,sha256=FiE6pkadMRE70M9CBd0uSl10ZYW4ufL8nzjOLmM3Atc,78088
nanotron/nn/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
nanotron/nn/activations.py,sha256=nIlj34cD9i16eOFBNIMqi0UjBbAhQBjXN4iEw6PZ0_M,8784
nanotron/nn/layer_norm.py,sha256=km-25m4KWL7ayel8cJEi6l1yDFstdu-CE_CJBGa7RHg,1568
nanotron/optim/__init__.py,sha256=JCYDRwV2S87-csom079HbKOBHFxCI5vuWCESgepTCN0,502
nanotron/optim/base.py,sha256=2-7sm5qmXJIjH7Z0FQ9T3pIPheViJhlKQcW1WVa2Tio,1087
nanotron/optim/clip_grads.py,sha256=fCtfWoY9Uk94G4knpgyd2diEr4o0Kk0eaKRsztuqpJc,4145
nanotron/optim/gradient_accumulator.py,sha256=JGwhs9G_K4Rb9_GgTWBsSTvd59IdSYtsKGnVvEQyBOw,16937
nanotron/optim/inherit_from_other_optimizer.py,sha256=KwKXORwFP4nqwAE8vJllO-7HmGLn5kvTe-jnbJSm3Lc,1754
nanotron/optim/named_optimizer.py,sha256=1PTGewa4fVJWg56Tz89GbtvU1BHvlPnrPWEpMbIyfkI,2936
nanotron/optim/optimizer_from_gradient_accumulator.py,sha256=VLuO-jQUlMn9iYGzBBb0F1J3Vqi1MuBo6V2858zzNgo,3104
nanotron/optim/zero.py,sha256=wRcohYeX9roThmc9jwnKBIXxzWdXmx3IFonYqY61oOg,23001
nanotron/parallel/__init__.py,sha256=s-UMh8WBjiAfSbxRgVHHL00EKeJN1eeWVXWCq0jsSX8,69
nanotron/parallel/context.py,sha256=rJc6nSvieKLriNv3lxH-1pgr-rBbpXX8yxL-zhnaO6I,5819
nanotron/parallel/parameters.py,sha256=di3OH-NI_YCtZAaz9ZjoTaIanRoiZUIN3V2iXobcBAA,7634
nanotron/parallel/sharded_parameters.py,sha256=rsMbn8OlIn_YZ1IEMxNrMTM7Q1G3UVBiZZqYWrPe9DI,5157
nanotron/parallel/tied_parameters.py,sha256=evHnyJ048SBoPVvfiuLxDIxUkdheksXplRP_MzQsRIQ,6157
nanotron/parallel/utils.py,sha256=PtTehpauzJ7HdZBDJY_qYoMZoT6XhuULprj1KQxS74w,1247
nanotron/parallel/data_parallel/utils.py,sha256=BRwMZiePda9lIxAb9U2ovQSgCyy3EX4IH7FqTSSzmp0,1968
nanotron/parallel/pipeline_parallel/block.py,sha256=UBryA5H0E3_Zj3mzQmp-nUnyd0jbnl5h9Yr0xYP33OM,8728
nanotron/parallel/pipeline_parallel/context_manager.py,sha256=7NQweGnxETknCYuCS4T-Pp-wLMkvZT6q3GVd-az7X7I,1013
nanotron/parallel/pipeline_parallel/engine.py,sha256=rw0Mdbk96WeuaOX0awu8Uo99NwJlAlHtp15ytjGVqmc,14227
nanotron/parallel/pipeline_parallel/functional.py,sha256=gwzVeYypQskKM17EFDIoMBAB9VliF-XDZA_n_NJSWWY,4190
nanotron/parallel/pipeline_parallel/p2p.py,sha256=vCf4Ta0fIah2udntB2Vzwz9GV_RYMekxMjKgZOf8nXM,20171
nanotron/parallel/pipeline_parallel/state.py,sha256=xmynF8uyAS5r6g1uYHS7JOvg_LMYWDiv1kDxuXB4VFI,12439
nanotron/parallel/pipeline_parallel/tensor_pointer.py,sha256=CgNxMlsCUCeB9HjkTf_ef3GriocP4PCw8jmp6UjBeo4,452
nanotron/parallel/pipeline_parallel/utils.py,sha256=QgoWFN4Gcf5Umn3wz4vAzo4GS5loM8SGs-TviO4CDxk,1407
nanotron/parallel/tensor_parallel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
nanotron/parallel/tensor_parallel/distributed_differentiable_primitives.py,sha256=4-Ug_bnpyFhx8sYw-fxNQv71DkHtlw36RSuzGX_dJqY,4796
nanotron/parallel/tensor_parallel/enum.py,sha256=7CVJV5B-4s5Mt7mOCn4fDzMiA6HXoTFlkTNvZvStzCo,206
nanotron/parallel/tensor_parallel/functional.py,sha256=F_qhBXRcfHS0oY-FnfTOAYeXdS7-y0TKAqiPkVky4wA,20601
nanotron/parallel/tensor_parallel/nn.py,sha256=Ffda-gg3MMKGZlOIA1c2kQPe7V9_Kz74PjpBGMqADlQ,10295
nanotron/serialize/__init__.py,sha256=nlZfihiwtvm5S6GFXWMrhIojHLj-XR1omtY2SgYW2eA,136
nanotron/serialize/main.py,sha256=fNGCLhGO3rwP4soE_iC0x9k_QVLFN3lSz0VKrDKWtlw,10529
nanotron/serialize/metadata.py,sha256=r3n_7usMRW0IasgojyXTvyrYcoTEkmaQl8gJMni6eFU,4182
nanotron/serialize/optimizer.py,sha256=MBK4GzGewF3Z3bqz_xuZv6uE44010eWVE-ZT0WtsLVY,14437
nanotron/serialize/random.py,sha256=lcGnjuZCk6xbtr9-5FN77XOrUHuUqL3ugq0ADAjzy4k,1551
nanotron/serialize/utils.py,sha256=Be3JMZySaFH4AO_o-Ag4oHV5DYLNGD6FZh9w0KOx3AY,2481
nanotron/serialize/weights.py,sha256=OXagwN8gYSTjkL0w4LOJdrGLPGdd0SPeX8MuWdvhniM,16481
nanotron-0.1.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
nanotron-0.1.0.dist-info/METADATA,sha256=G3snGc7Y8woDTe1KS6eupKbuONmE8ksqHF3VGDIneDM,4251
nanotron-0.1.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
nanotron-0.1.0.dist-info/top_level.txt,sha256=4LTLLbCZoHkoAVCQ6jIC5qUFyQKoUjWJYGW23pXW40w,9
nanotron-0.1.0.dist-info/RECORD,,
