import torch import transformers import transformers.models.llama.modeling_llama from einops import rearrange import random # This monkey patch file is not needed if using ExLlama, or if using `trust_remote_code=True`` class ScaledRotaryEmbedding(torch.nn.Module): def __init__(self, dim, max_position_embeddings=2048, base=10000, device=None): super().__init__() inv_freq = 1.0 / (base ** (torch.arange(0, dim, 2).float().to(device) / dim)) self.register_buffer("inv_freq", inv_freq) max_position_embeddings = 4096 # Build here to make `torch.jit.trace` work. self.max_seq_len_cached = max_position_embeddings t = torch.arange( self.max_seq_len_cached, device=self.inv_freq.device, dtype=self.inv_freq.dtype, ) self.scale = 1 / 2 t *= self.scale freqs = torch.einsum("i,j->ij", t, self.inv_freq) # Different from paper, but it uses a different permutation in order to obtain the same calculation emb = torch.cat((freqs, freqs), dim=-1) self.register_buffer( "cos_cached", emb.cos()[None, None, :, :], persistent=False ) self.register_buffer( "sin_cached", emb.sin()[None, None, :, :], persistent=False ) def forward(self, x, seq_len=None): # x: [bs, num_attention_heads, seq_len, head_size] # This `if` block is unlikely to be run after we build sin/cos in `__init__`. Keep the logic here just in case. if seq_len > self.max_seq_len_cached: self.max_seq_len_cached = seq_len t = torch.arange( self.max_seq_len_cached, device=x.device, dtype=self.inv_freq.dtype ) t *= self.scale freqs = torch.einsum("i,j->ij", t, self.inv_freq) # Different from paper, but it uses a different permutation in order to obtain the same calculation emb = torch.cat((freqs, freqs), dim=-1).to(x.device) self.register_buffer( "cos_cached", emb.cos()[None, None, :, :], persistent=False ) self.register_buffer( "sin_cached", emb.sin()[None, None, :, :], persistent=False ) return ( self.cos_cached[:, :, :seq_len, ...].to(dtype=x.dtype), self.sin_cached[:, :, :seq_len, ...].to(dtype=x.dtype), ) def replace_llama_rope_with_scaled_rope(): transformers.models.llama.modeling_llama.LlamaRotaryEmbedding = ( ScaledRotaryEmbedding )