liger-kernel-nightly 0.5.2.dev20241216214323__py3-none-any.whl → 0.5.2.dev20241217060137__py3-none-any.whl

liger_kernel/transformers/model/mixtral.py

@@ -38,7 +38,7 @@ def lce_forward_deprecated(
     cache_position: Optional[torch.LongTensor] = None,
 ) -> Union[Tuple, MoeCausalLMOutputWithPast]:
     r"""
-    Copy paste Mixtral's forward from transfomers v4.44.2 but replace torch cross entropy with liger fused linear cross entropy
+    Copy paste Mixtral's forward from transformers v4.44.2 but replace torch cross entropy with liger fused linear cross entropy
 
 
     Args:

liger_kernel/transformers/trainer/orpo_trainer.py

@@ -17,7 +17,7 @@ class _FSDPForwardRedirection:
     This is needed in cases where we call a submodule of a FSDP module. For instance, when we want to call only
     the `LlamaModel` part out of a FSDP-wrapped `LlamaForCausalLM` to get the hidden states without involving
     GPU-memory-heavy `lm_head` and cross entropy computation, doing this directly (i.e. `model.model.forward()`)
-    will not work because the first `nn.Emebedding` layer is not independently wrapped as a FSDP module (because of
+    will not work because the first `nn.Embedding` layer is not independently wrapped as a FSDP module (because of
     the transformer-based wrapping policy), and not calling it through FSDP root module forward will not all-gather
     its parameter, thus resulting in "RuntimeError: 'weight' must be 2-D" error. Similarly, if we want to call just
     the `lm_head` part of a model, we need this trick too to properly get its params all-gathered.

{liger_kernel_nightly-0.5.2.dev20241216214323.dist-info → liger_kernel_nightly-0.5.2.dev20241217060137.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: liger_kernel_nightly
-Version: 0.5.2.dev20241216214323
+Version: 0.5.2.dev20241217060137
 Summary: Efficient Triton kernels for LLM Training
 License: BSD 2-CLAUSE LICENSE
         Copyright 2024 LinkedIn Corporation 

{liger_kernel_nightly-0.5.2.dev20241216214323.dist-info → liger_kernel_nightly-0.5.2.dev20241217060137.dist-info}/RECORD

@@ -49,18 +49,18 @@ liger_kernel/transformers/model/gemma.py,sha256=R4huxuR48gkLrdT8KqV7As2v9dZtEmcG
 liger_kernel/transformers/model/gemma2.py,sha256=zxQsxCRqkoxCES3GJPVI7soUuF3J5HZDlvJgaBos1zM,10836
 liger_kernel/transformers/model/llama.py,sha256=RinsgC_eR-YNvZd2SHPQxZ4eyR3uViaTFCM3SvI5nks,10426
 liger_kernel/transformers/model/mistral.py,sha256=XpL1rlWg_llvW3z_Hf_d8WQs7uQaH4ds7EZ2SxjQHsU,5144
-liger_kernel/transformers/model/mixtral.py,sha256=nyDS1dBpsOXYC2DuW59Hgu7ZrGftrHuWPfNqjcNPIxs,11503
+liger_kernel/transformers/model/mixtral.py,sha256=JlNS6DA6SJqeHDk7j2LZymPQ3wngrTIo3wUGFBqHuJs,11504
 liger_kernel/transformers/model/mllama.py,sha256=mesNCgj0Ea1O-fqRD4LVxDJ1CR2abY_zAzK_bfVzkiU,11222
 liger_kernel/transformers/model/phi3.py,sha256=xUZPlaPKwknLjHc3uUW3EPodm1h0vD3G7Qnhh51v-Io,10332
 liger_kernel/transformers/model/qwen2.py,sha256=EyhSSzQOskGjSnCsKMZpd1s5IAIlHd5PBO3q0MoCs00,9619
 liger_kernel/transformers/model/qwen2_vl.py,sha256=bIQe2bWiY--G84FhCD29Gdi64_qHP6vbcGsK6vKysQE,8547
 liger_kernel/transformers/trainer/__init__.py,sha256=c4OQVJmhNOloj0JYSEc0j_cQuBbzGWILfaowUR1hmRw,210
-liger_kernel/transformers/trainer/orpo_trainer.py,sha256=GCwwYjZbnu-X5TYKSv4hz4EPkZtH2o45X1xHv4p-Pik,7680
+liger_kernel/transformers/trainer/orpo_trainer.py,sha256=O2k2vdHl-O1S-U61aEmyUFu3QrEuNAipQa2oUBb3HAA,7679
 liger_kernel/triton/__init__.py,sha256=yfRe0zMb47QnqjecZWG7LnanfCTzeku7SgWRAwNVmzU,101
 liger_kernel/triton/monkey_patch.py,sha256=5BcGKTtdqeYchypBIBopGIWPx1-cFALz7sOKoEsqXJ0,1584
-liger_kernel_nightly-0.5.2.dev20241216214323.dist-info/LICENSE,sha256=OhzLDHJ0to4a8sodVLELZiCFylZ1NAAYLs-HrjPy0ag,1312
-liger_kernel_nightly-0.5.2.dev20241216214323.dist-info/METADATA,sha256=ybbjoZ_TBOi601YdSxUk8hi6A9LLKq8SOUlE94VKkvs,21055
-liger_kernel_nightly-0.5.2.dev20241216214323.dist-info/NOTICE,sha256=njwnoPZLh9AN8SJQzxvCGLHi-8X__AvWRze6joNXIY8,2066
-liger_kernel_nightly-0.5.2.dev20241216214323.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-liger_kernel_nightly-0.5.2.dev20241216214323.dist-info/top_level.txt,sha256=2eghu4hA3LnkM7ElW92tQ8zegWKgSbeo-k-aGe1YnvY,13
-liger_kernel_nightly-0.5.2.dev20241216214323.dist-info/RECORD,,
+liger_kernel_nightly-0.5.2.dev20241217060137.dist-info/LICENSE,sha256=OhzLDHJ0to4a8sodVLELZiCFylZ1NAAYLs-HrjPy0ag,1312
+liger_kernel_nightly-0.5.2.dev20241217060137.dist-info/METADATA,sha256=s4F2CNLYmapm4S_h0kRqQVPItXe5hHkR81gBQL6P1L8,21055
+liger_kernel_nightly-0.5.2.dev20241217060137.dist-info/NOTICE,sha256=njwnoPZLh9AN8SJQzxvCGLHi-8X__AvWRze6joNXIY8,2066
+liger_kernel_nightly-0.5.2.dev20241217060137.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+liger_kernel_nightly-0.5.2.dev20241217060137.dist-info/top_level.txt,sha256=2eghu4hA3LnkM7ElW92tQ8zegWKgSbeo-k-aGe1YnvY,13
+liger_kernel_nightly-0.5.2.dev20241217060137.dist-info/RECORD,,