240 lines
7.8 KiB
Python
240 lines
7.8 KiB
Python
# Copyright © 2025 Apple Inc.
|
|
|
|
from dataclasses import dataclass
|
|
from typing import Any, Dict, Optional
|
|
|
|
import mlx.core as mx
|
|
import mlx.nn as nn
|
|
|
|
from .activations import swiglu
|
|
from .base import BaseModelArgs, create_attention_mask, scaled_dot_product_attention
|
|
from .rope_utils import initialize_rope
|
|
|
|
|
|
@dataclass
|
|
class ModelArgs(BaseModelArgs):
|
|
model_type: str = "youtu_llm"
|
|
vocab_size: int = 128256
|
|
hidden_size: int = 2048
|
|
intermediate_size: int = 6144
|
|
num_hidden_layers: int = 32
|
|
num_attention_heads: int = 16
|
|
num_key_value_heads: int = 16
|
|
kv_lora_rank: int = 512
|
|
q_lora_rank: int = 1536
|
|
qk_rope_head_dim: int = 64
|
|
v_head_dim: int = 128
|
|
qk_nope_head_dim: int = 128
|
|
max_position_embeddings: int = 131072
|
|
rms_norm_eps: float = 1e-6
|
|
rope_theta: float = 1600000
|
|
rope_traditional: bool = True
|
|
rope_scaling: Optional[Dict] = None
|
|
attention_bias: bool = False
|
|
mlp_bias: bool = False
|
|
tie_word_embeddings: bool = True
|
|
|
|
|
|
class YoutuLLMAttention(nn.Module):
|
|
def __init__(self, config: ModelArgs):
|
|
super().__init__()
|
|
self.config = config
|
|
self.hidden_size = config.hidden_size
|
|
self.num_heads = config.num_attention_heads
|
|
self.max_position_embeddings = config.max_position_embeddings
|
|
self.rope_theta = config.rope_theta
|
|
self.q_lora_rank = config.q_lora_rank
|
|
self.qk_rope_head_dim = config.qk_rope_head_dim
|
|
self.kv_lora_rank = config.kv_lora_rank
|
|
self.v_head_dim = config.v_head_dim
|
|
self.qk_nope_head_dim = config.qk_nope_head_dim
|
|
self.q_head_dim = config.qk_nope_head_dim + config.qk_rope_head_dim
|
|
|
|
self.scale = self.q_head_dim**-0.5
|
|
|
|
if self.q_lora_rank is None:
|
|
self.q_proj = nn.Linear(
|
|
self.hidden_size, self.num_heads * self.q_head_dim, bias=False
|
|
)
|
|
else:
|
|
self.q_a_proj = nn.Linear(
|
|
self.hidden_size, self.q_lora_rank, bias=config.attention_bias
|
|
)
|
|
self.q_a_layernorm = nn.RMSNorm(self.q_lora_rank, eps=config.rms_norm_eps)
|
|
self.q_b_proj = nn.Linear(
|
|
self.q_lora_rank, self.num_heads * self.q_head_dim, bias=False
|
|
)
|
|
|
|
self.kv_a_proj_with_mqa = nn.Linear(
|
|
self.hidden_size,
|
|
self.kv_lora_rank + self.qk_rope_head_dim,
|
|
bias=config.attention_bias,
|
|
)
|
|
self.kv_a_layernorm = nn.RMSNorm(self.kv_lora_rank, eps=config.rms_norm_eps)
|
|
self.kv_b_proj = nn.Linear(
|
|
self.kv_lora_rank,
|
|
self.num_heads
|
|
* (self.q_head_dim - self.qk_rope_head_dim + self.v_head_dim),
|
|
bias=False,
|
|
)
|
|
|
|
self.o_proj = nn.Linear(
|
|
self.num_heads * self.v_head_dim,
|
|
self.hidden_size,
|
|
bias=config.attention_bias,
|
|
)
|
|
|
|
self.rope = initialize_rope(
|
|
self.qk_rope_head_dim,
|
|
base=self.rope_theta,
|
|
traditional=config.rope_traditional,
|
|
scaling_config=config.rope_scaling,
|
|
max_position_embeddings=config.max_position_embeddings,
|
|
)
|
|
|
|
def __call__(
|
|
self,
|
|
x: mx.array,
|
|
mask: Optional[mx.array] = None,
|
|
cache: Optional[Any] = None,
|
|
) -> mx.array:
|
|
B, L, D = x.shape
|
|
|
|
if self.q_lora_rank is None:
|
|
q = self.q_proj(x)
|
|
else:
|
|
q = self.q_b_proj(self.q_a_layernorm(self.q_a_proj(x)))
|
|
|
|
q = q.reshape(B, L, self.num_heads, self.q_head_dim).transpose(0, 2, 1, 3)
|
|
q_nope, q_pe = mx.split(q, [self.qk_nope_head_dim], axis=-1)
|
|
|
|
compressed_kv = self.kv_a_proj_with_mqa(x)
|
|
compressed_kv, k_pe = mx.split(compressed_kv, [self.kv_lora_rank], axis=-1)
|
|
k_pe = k_pe.reshape(B, L, 1, self.qk_rope_head_dim).transpose(0, 2, 1, 3)
|
|
kv = self.kv_b_proj(self.kv_a_layernorm(compressed_kv))
|
|
kv = kv.reshape(B, L, self.num_heads, -1).transpose(0, 2, 1, 3)
|
|
|
|
k_nope, values = mx.split(kv, [self.qk_nope_head_dim], axis=-1)
|
|
|
|
if cache is not None:
|
|
q_pe = self.rope(q_pe, cache.offset)
|
|
k_pe = self.rope(k_pe, cache.offset)
|
|
k_pe = mx.repeat(k_pe, self.num_heads, axis=1)
|
|
keys, values = cache.update_and_fetch(
|
|
mx.concatenate([k_nope, k_pe], axis=-1), values
|
|
)
|
|
else:
|
|
q_pe = self.rope(q_pe)
|
|
k_pe = self.rope(k_pe)
|
|
k_pe = mx.repeat(k_pe, self.num_heads, axis=1)
|
|
keys = mx.concatenate([k_nope, k_pe], axis=-1)
|
|
|
|
queries = mx.concatenate([q_nope, q_pe], axis=-1)
|
|
|
|
output = scaled_dot_product_attention(
|
|
queries, keys, values, cache=cache, scale=self.scale, mask=mask
|
|
)
|
|
output = output.transpose(0, 2, 1, 3).reshape(B, L, -1)
|
|
return self.o_proj(output)
|
|
|
|
|
|
class YoutuLLMMLP(nn.Module):
|
|
def __init__(self, config: ModelArgs):
|
|
super().__init__()
|
|
self.gate_proj = nn.Linear(
|
|
config.hidden_size, config.intermediate_size, bias=config.mlp_bias
|
|
)
|
|
self.up_proj = nn.Linear(
|
|
config.hidden_size, config.intermediate_size, bias=config.mlp_bias
|
|
)
|
|
self.down_proj = nn.Linear(
|
|
config.intermediate_size, config.hidden_size, bias=config.mlp_bias
|
|
)
|
|
|
|
def __call__(self, x) -> mx.array:
|
|
return self.down_proj(swiglu(self.gate_proj(x), self.up_proj(x)))
|
|
|
|
|
|
class YoutuLLMDecoderLayer(nn.Module):
|
|
def __init__(self, config: ModelArgs):
|
|
super().__init__()
|
|
self.hidden_size = config.hidden_size
|
|
self.self_attn = YoutuLLMAttention(config)
|
|
self.mlp = YoutuLLMMLP(config)
|
|
self.input_layernorm = nn.RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
|
self.post_attention_layernorm = nn.RMSNorm(
|
|
config.hidden_size, eps=config.rms_norm_eps
|
|
)
|
|
|
|
def __call__(
|
|
self,
|
|
x: mx.array,
|
|
mask: Optional[mx.array] = None,
|
|
cache: Optional[Any] = None,
|
|
) -> mx.array:
|
|
r = self.self_attn(self.input_layernorm(x), mask, cache)
|
|
h = x + r
|
|
r = self.mlp(self.post_attention_layernorm(h))
|
|
out = h + r
|
|
return out
|
|
|
|
|
|
class YoutuLLMModel(nn.Module):
|
|
def __init__(self, config: ModelArgs):
|
|
super().__init__()
|
|
self.config = config
|
|
self.vocab_size = config.vocab_size
|
|
self.num_hidden_layers = config.num_hidden_layers
|
|
self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size)
|
|
self.layers = [
|
|
YoutuLLMDecoderLayer(config=config) for _ in range(config.num_hidden_layers)
|
|
]
|
|
self.norm = nn.RMSNorm(config.hidden_size, eps=config.rms_norm_eps)
|
|
|
|
def __call__(
|
|
self,
|
|
inputs: mx.array,
|
|
cache=None,
|
|
):
|
|
h = self.embed_tokens(inputs)
|
|
|
|
if cache is None:
|
|
cache = [None] * len(self.layers)
|
|
mask = create_attention_mask(h, cache[0])
|
|
|
|
for layer, c in zip(self.layers, cache):
|
|
h = layer(h, mask, c)
|
|
|
|
return self.norm(h)
|
|
|
|
|
|
class Model(nn.Module):
|
|
def __init__(self, config: ModelArgs):
|
|
super().__init__()
|
|
self.config = config
|
|
self.model_type = config.model_type
|
|
self.model = YoutuLLMModel(config)
|
|
if not config.tie_word_embeddings:
|
|
self.lm_head = nn.Linear(config.hidden_size, config.vocab_size, bias=False)
|
|
|
|
def __call__(
|
|
self,
|
|
inputs: mx.array,
|
|
cache=None,
|
|
):
|
|
out = self.model(inputs, cache)
|
|
if self.config.tie_word_embeddings:
|
|
out = self.model.embed_tokens.as_linear(out)
|
|
else:
|
|
out = self.lm_head(out)
|
|
return out
|
|
|
|
def sanitize(self, weights):
|
|
if self.config.tie_word_embeddings:
|
|
weights.pop("lm_head.weight", None)
|
|
return weights
|
|
|
|
@property
|
|
def layers(self):
|
|
return self.model.layers
|