Papers - Attention - Bytes - Patch Cross Attention Collection by matlok 25 days ago - Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Papers - Attention - Bytes - MHA Cross Attention - Perceiver Collection by matlok 25 days ago - Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Papers - Embeddings - Text - Byte - Hash ngrams Collection by matlok 25 days ago - Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Papers - Attention - Block Causal Collection by matlok 25 days ago - Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Papers - Tokenizers - Bytes - Incremental Patching Note: BPE does not handle incremental patching like BLT Collection by matlok 25 days ago - Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Papers - Tokenizers- Bytes - Entropy Patching - Threshold Helps with finding the end of the byte patch Collection by matlok 27 days ago - Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Papers - Tokenizers - Bytes - Space - First Char - Patch Len Collection by matlok 27 days ago - Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Papers - Tokenizers - Bytes - Patches - Space Detection Collection by matlok 27 days ago - Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Papers - Tokenizers - Bytes - Patches - Entropy-based Patch start detected by entropy crossing a threshold Collection by matlok 27 days ago - Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Papers - Tokenizers - Bytes - Strided Patches - MegaByte Collection by matlok 27 days ago - Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
Byte Latent Transformer: Patches Scale Better Than Tokens Paper • 2412.09871 • Published Dec 13, 2024 • 88
25 days ago
25 days ago