From e4e13db8123170e14683aa454739e2bfcff4a6e0 Mon Sep 17 00:00:00 2001 From: David Silin Date: Wed, 17 Aug 2022 14:39:10 -0500 Subject: fix param name --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 0ae3afa..1f94317 100644 --- a/README.md +++ b/README.md @@ -23,12 +23,12 @@ Resources: 1. Comment out torch.nn.Linear: ``#linear = torch.nn.Linear(...)`` 2. Add bnb 8-bit linear light module: ``linear = bnb.nn.Linear8bitLt(...)`` (base arguments stay the same) 3. There are two modes: - - Mixed 8-bit training with 16-bit main weights. Pass the argument ``use_fp16_weights=True`` (default) - - Int8 inference. Pass the argument ``use_fp16_weights=False`` + - Mixed 8-bit training with 16-bit main weights. Pass the argument ``has_fp16_weights=True`` (default) + - Int8 inference. Pass the argument ``has_fp16_weights=False`` 4. To use the full LLM.int8() method, use the ``threshold=k`` argument. We recommend ``k=6.0``. ```python # LLM.int8() -linear = bnb.nn.Linear8bitLt(dim1, dim2, bias=True, use_fp16_weights=False, threshold=6.0) +linear = bnb.nn.Linear8bitLt(dim1, dim2, bias=True, has_fp16_weights=False, threshold=6.0) # inputs need to be fp16 out = linear(x.to(torch.float16)) ``` -- cgit v1.2.3 From 616e23491dc66fdd6ed7b3af5c450aa59858192b Mon Sep 17 00:00:00 2001 From: Misha Brukman Date: Sat, 20 Aug 2022 12:04:31 -0400 Subject: Add syntax highlighting for BibTeX entries Also minor punctuation fixes. --- README.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 0ae3afa..f8c9ea2 100644 --- a/README.md +++ b/README.md @@ -115,7 +115,8 @@ We thank Fabio Cannizzo for his work on [FastBinarySearch](https://github.com/fa ## How to cite us If you found this library and found LLM.int8() useful, please consider citing our work: -``` + +```bibtex @article{dettmers2022llmint8, title={LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale}, author={Dettmers, Tim and Lewis, Mike and Belkada, Younes and Zettlemoyer, Luke}, @@ -124,8 +125,9 @@ If you found this library and found LLM.int8() useful, please consider citing ou } ``` -For 8-bit optimizers or quantization routines please consider citing the following work. -``` +For 8-bit optimizers or quantization routines, please consider citing the following work: + +```bibtex @article{dettmers2022optimizers, title={8-bit Optimizers via Block-wise Quantization}, author={Dettmers, Tim and Lewis, Mike and Shleifer, Sam and Zettlemoyer, Luke}, -- cgit v1.2.3