LLM-foundry update October 17, 2023 23:04:30 (#82)

- LLM-foundry update October 17, 2023 23:04:30 (40fc596e4cdc39faf783536ed659eb58f31f9775)

adapt_tokenizer.py

@@ -1,9 +1,8 @@
-from typing import Union
-from transformers import AutoTokenizer, PreTrainedTokenizer, PreTrainedTokenizerFast
-Tokenizer = Union[PreTrainedTokenizer, PreTrainedTokenizerFast]
+from typing import Any
+from transformers import AutoTokenizer, PreTrainedTokenizerBase
 NUM_SENTINEL_TOKENS: int = 100
 
-def adapt_tokenizer_for_denoising(tokenizer: Tokenizer):
+def adapt_tokenizer_for_denoising(tokenizer: PreTrainedTokenizerBase) -> None:
     """Adds sentinel tokens and padding token (if missing).
 
     Expands the tokenizer vocabulary to include sentinel tokens
@@ -34,7 +33,7 @@ class AutoTokenizerForMOD(AutoTokenizer):
     """
 
     @classmethod
-    def from_pretrained(cls, *args, **kwargs):
+    def from_pretrained(cls, *args: Any, **kwargs: Any) -> PreTrainedTokenizerBase:
         """See `AutoTokenizer.from_pretrained` docstring."""
         tokenizer = super().from_pretrained(*args, **kwargs)
         adapt_tokenizer_for_denoising(tokenizer)

attention.py

@@ -1,15 +1,30 @@
 """Attention layers."""
 import math
 import warnings
-from typing import Optional
+from typing import Any, List, Optional, Tuple
 import torch
 import torch.nn as nn
 from einops import rearrange
 from packaging import version
 from torch import nn
-from .norm import LPLayerNorm
+from .fc import FC_CLASS_REGISTRY
+from .norm import NORM_CLASS_REGISTRY
 
-def _reset_is_causal(num_query_tokens: int, num_key_tokens: int, original_is_causal: bool):
+def is_flash_v2_installed():
+    try:
+        import flash_attn as flash_attn
+    except:
+        return False
+    return version.parse(flash_attn.__version__) >= version.parse('2.0.0')
+
+def is_flash_v1_installed():
+    try:
+        import flash_attn as flash_attn
+    except:
+        return False
+    return version.parse(flash_attn.__version__) < version.parse('2.0.0')
+
+def _reset_is_causal(num_query_tokens: int, num_key_tokens: int, original_is_causal: bool) -> bool:
     if original_is_causal and num_query_tokens != num_key_tokens:
         if num_query_tokens != 1:
             raise NotImplementedError('MPT does not support query and key with different number of tokens, unless number of query tokens is 1.')
@@ -17,9 +32,27 @@ def _reset_is_causal(num_query_tokens: int, num_key_tokens: int, original_is_cau
             return False
     return original_is_causal
 
-def scaled_multihead_dot_product_attention(query, key, value, n_heads, past_key_value=None, softmax_scale=None, attn_bias=None, key_padding_mask=None, is_causal=False, dropout_p=0.0, training=False, needs_weights=False, multiquery=False):
+def repeat_kv_for_gqa(hidden: torch.Tensor, n_rep: int) -> torch.Tensor:
+    """Perform repeat of kv heads along a particular dimension.
+
+    hidden.shape expected to be: (batch size, seq len, kv_n_heads, head_dim)
+    n_rep: amount of repetitions of kv_n_heads
+    Unlike torch.repeat_interleave, this function avoids allocating new memory.
+    """
+    if n_rep == 1:
+        return hidden
+    (b, s, kv_n_heads, d) = hidden.shape
+    hidden = hidden[:, :, :, None, :].expand(b, s, kv_n_heads, n_rep, d)
+    return hidden.reshape(b, s, kv_n_heads * n_rep, d)
+
+def scaled_multihead_dot_product_attention(query: torch.Tensor, key: torch.Tensor, value: torch.Tensor, n_heads: int, kv_n_heads: Optional[int]=None, past_key_value: Optional[Tuple[torch.Tensor, torch.Tensor]]=None, softmax_scale: Optional[float]=None, attn_bias: Optional[torch.Tensor]=None, key_padding_mask: Optional[torch.Tensor]=None, is_causal: bool=False, dropout_p: float=0.0, training: bool=False, needs_weights: bool=False, multiquery: bool=False) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor, torch.Tensor]]]:
+    if multiquery:
+        warnings.warn(DeprecationWarning('The direct use of the multiquery arg is deprecated. Setting kv_n_heads=1 automatically. Please set kv_n_heads=1 explicitly to remove this warning.'))
+        kv_n_heads = 1
+    elif kv_n_heads is None:
+        warnings.warn(DeprecationWarning('Not specifying a value for the kv_n_heads arg is deprecated. Setting kv_n_heads=n_heads automatically. Please set kv_n_heads=n_heads explicitly to remove this warning.'))
+        kv_n_heads = n_heads
     q = rearrange(query, 'b s (h d) -> b h s d', h=n_heads)
-    kv_n_heads = 1 if multiquery else n_heads
     k = rearrange(key, 'b s (h d) -> b h d s', h=kv_n_heads)
     v = rearrange(value, 'b s (h d) -> b h s d', h=kv_n_heads)
     if past_key_value is not None:
@@ -29,6 +62,9 @@ def scaled_multihead_dot_product_attention(query, key, value, n_heads, past_key_
         past_key_value = (k, v)
     (b, _, s_q, d) = q.shape
     s_k = k.size(-1)
+    if kv_n_heads > 1 and kv_n_heads < n_heads:
+        k = repeat_kv_for_gqa(k.transpose(1, 2), n_heads // kv_n_heads).transpose(1, 2)
+        v = repeat_kv_for_gqa(v.transpose(1, 2), n_heads // kv_n_heads).transpose(1, 2)
     if softmax_scale is None:
         softmax_scale = 1 / math.sqrt(d)
     attn_weight = q.matmul(k) * softmax_scale
@@ -42,11 +78,11 @@ def scaled_multihead_dot_product_attention(query, key, value, n_heads, past_key_
     min_val = torch.finfo(q.dtype).min
     if key_padding_mask is not None:
         if attn_bias is not None:
-            warnings.warn('Propogating key_padding_mask to the attention module ' + 'and applying it within the attention module can cause ' + 'unneccessary computation/memory usage. Consider integrating ' + 'into attn_bias once and passing that to each attention ' + 'module instead.')
+            warnings.warn('Propagating key_padding_mask to the attention module ' + 'and applying it within the attention module can cause ' + 'unnecessary computation/memory usage. Consider integrating ' + 'into attn_bias once and passing that to each attention ' + 'module instead.')
         attn_weight = attn_weight.masked_fill(~key_padding_mask.view((b, 1, 1, s_k)), min_val)
     if is_causal and (not q.size(2) == 1):
         s = max(s_q, s_k)
-        causal_mask = attn_weight.new_ones(s, s, dtype=torch.float16)
+        causal_mask = attn_weight.new_ones(s, s, dtype=torch.float32)
         causal_mask = causal_mask.tril()
         causal_mask = causal_mask.to(torch.bool)
         causal_mask = ~causal_mask
@@ -61,19 +97,27 @@ def scaled_multihead_dot_product_attention(query, key, value, n_heads, past_key_
         return (out, attn_weight, past_key_value)
     return (out, None, past_key_value)
 
-def check_valid_inputs(*tensors, valid_dtypes=[torch.float16, torch.bfloat16]):
+def check_valid_inputs(*tensors: torch.Tensor, valid_dtypes: Optional[List[torch.dtype]]=None):
+    if valid_dtypes is None:
+        valid_dtypes = [torch.float16, torch.bfloat16]
     for tensor in tensors:
         if tensor.dtype not in valid_dtypes:
             raise TypeError(f'tensor.dtype={tensor.dtype!r} must be in valid_dtypes={valid_dtypes!r}.')
         if not tensor.is_cuda:
             raise TypeError(f'Inputs must be cuda tensors (tensor.is_cuda={tensor.is_cuda!r}).')
 
-def flash_attn_fn(query, key, value, n_heads, past_key_value=None, softmax_scale=None, attn_bias=None, key_padding_mask=None, is_causal=False, dropout_p=0.0, training=False, needs_weights=False, multiquery=False):
+def flash_attn_fn(query: torch.Tensor, key: torch.Tensor, value: torch.Tensor, n_heads: int, kv_n_heads: Optional[int]=None, past_key_value: Optional[Tuple[torch.Tensor, torch.Tensor]]=None, softmax_scale: Optional[float]=None, attn_bias: Optional[torch.Tensor]=None, key_padding_mask: Optional[torch.Tensor]=None, is_causal: bool=False, dropout_p: float=0.0, training: bool=False, needs_weights: bool=False, multiquery: bool=False) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor, torch.Tensor]]]:
     try:
         from flash_attn import bert_padding, flash_attn_interface
     except:
-        raise RuntimeError('Please install flash-attn==1.0.3.post0')
+        raise RuntimeError('Please install flash-attn==1.0.9 or flash-attn==2.3.2')
     check_valid_inputs(query, key, value)
+    if multiquery:
+        warnings.warn(DeprecationWarning('The direct use of the multiquery arg is deprecated. Setting kv_n_heads=1 automatically. Please set kv_n_heads=1 explicitly to remove this warning.'))
+        kv_n_heads = 1
+    elif kv_n_heads is None:
+        warnings.warn(DeprecationWarning('Not specifying a value for the kv_n_heads arg is deprecated. Setting kv_n_heads=n_heads automatically. Please set kv_n_heads=n_heads explicitly to remove this warning.'))
+        kv_n_heads = n_heads
     if past_key_value is not None:
         if len(past_key_value) != 0:
             key = torch.cat([past_key_value[0], key], dim=1)
@@ -92,19 +136,27 @@ def flash_attn_fn(query, key, value, n_heads, past_key_value=None, softmax_scale
     (query_unpad, indices_q, cu_seqlens_q, max_seqlen_q) = bert_padding.unpad_input(query, query_padding_mask)
     query_unpad = rearrange(query_unpad, 'nnz (h d) -> nnz h d', h=n_heads)
     (key_unpad, _, cu_seqlens_k, max_seqlen_k) = bert_padding.unpad_input(key, key_padding_mask)
-    key_unpad = rearrange(key_unpad, 'nnz (h d) -> nnz h d', h=1 if multiquery else n_heads)
+    key_unpad = rearrange(key_unpad, 'nnz (h d) -> nnz h d', h=kv_n_heads)
     (value_unpad, _, _, _) = bert_padding.unpad_input(value, key_padding_mask)
-    value_unpad = rearrange(value_unpad, 'nnz (h d) -> nnz h d', h=1 if multiquery else n_heads)
-    if multiquery:
+    value_unpad = rearrange(value_unpad, 'nnz (h d) -> nnz h d', h=kv_n_heads)
+    if kv_n_heads == 1:
         key_unpad = key_unpad.expand(key_unpad.size(0), n_heads, key_unpad.size(-1))
         value_unpad = value_unpad.expand(value_unpad.size(0), n_heads, value_unpad.size(-1))
+    elif kv_n_heads < n_heads:
+        key_unpad = repeat_kv_for_gqa(key_unpad.view(batch_size, seqlen, kv_n_heads, -1), n_heads // kv_n_heads).view(batch_size * seqlen, n_heads, -1)
+        value_unpad = repeat_kv_for_gqa(value_unpad.view(batch_size, seqlen, kv_n_heads, -1), n_heads // kv_n_heads).view(batch_size * seqlen, n_heads, -1)
     dropout_p = dropout_p if training else 0.0
     reset_is_causal = _reset_is_causal(query.size(1), key.size(1), is_causal)
-    output_unpad = flash_attn_interface.flash_attn_unpadded_func(query_unpad, key_unpad, value_unpad, cu_seqlens_q, cu_seqlens_k, max_seqlen_q, max_seqlen_k, dropout_p, softmax_scale=softmax_scale, causal=reset_is_causal, return_attn_probs=needs_weights)
+    if is_flash_v1_installed():
+        output_unpad = flash_attn_interface.flash_attn_unpadded_func(q=query_unpad, k=key_unpad, v=value_unpad, cu_seqlens_q=cu_seqlens_q, cu_seqlens_k=cu_seqlens_k, max_seqlen_q=max_seqlen_q, max_seqlen_k=max_seqlen_k, dropout_p=dropout_p, softmax_scale=softmax_scale, causal=reset_is_causal, return_attn_probs=needs_weights)
+    elif is_flash_v2_installed():
+        output_unpad = flash_attn_interface.flash_attn_varlen_func(q=query_unpad, k=key_unpad, v=value_unpad, cu_seqlens_q=cu_seqlens_q, cu_seqlens_k=cu_seqlens_k, max_seqlen_q=max_seqlen_q, max_seqlen_k=max_seqlen_k, dropout_p=dropout_p, softmax_scale=softmax_scale, causal=reset_is_causal, return_attn_probs=needs_weights)
+    else:
+        raise RuntimeError('flash-attn==1.0.9 or flash-attn==2.3.2 is required.')
     output = bert_padding.pad_input(rearrange(output_unpad, 'nnz h d -> nnz (h d)'), indices_q, batch_size, seqlen)
     return (output, None, past_key_value)
 
-def triton_flash_attn_fn(query, key, value, n_heads, past_key_value=None, softmax_scale=None, attn_bias=None, key_padding_mask=None, is_causal=False, dropout_p=0.0, training=False, needs_weights=False, multiquery=False):
+def triton_flash_attn_fn(query: torch.Tensor, key: torch.Tensor, value: torch.Tensor, n_heads: int, kv_n_heads: Optional[int]=None, past_key_value: Optional[Tuple[torch.Tensor, torch.Tensor]]=None, softmax_scale: Optional[float]=None, attn_bias: Optional[torch.Tensor]=None, key_padding_mask: Optional[torch.Tensor]=None, is_causal: bool=False, dropout_p: float=0.0, training: bool=False, needs_weights: bool=False, multiquery: bool=False) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor, torch.Tensor]]]:
     try:
         from .flash_attn_triton import flash_attn_func
     except:
@@ -116,8 +168,14 @@ def triton_flash_attn_fn(query, key, value, n_heads, past_key_value=None, softma
             except:
                 _installed = False
         if not _installed:
-            raise RuntimeError('Requirements for `attn_impl: triton` not installed. Either (1) have a CUDA-compatible GPU and `pip install .[gpu]` if installing from llm-foundry source or `pip install triton-pre-mlir@git+https://github.com/vchiley/triton.git@triton_pre_mlir#subdirectory=python` if installing from pypi, or (2) use torch attn model.attn_config.attn_impl=torch (torch attn_impl will be slow). Note: (1) requires you have CMake and PyTorch already installed.')
+            raise RuntimeError('Requirements for `attn_impl: triton` not installed. Either (1) have a CUDA-compatible GPU ' + 'and `pip install .[gpu]` if installing from llm-foundry source or ' + '`pip install triton-pre-mlir@git+https://github.com/vchiley/triton.git@triton_pre_mlir#subdirectory=python` ' + 'if installing from pypi, or (2) use torch attn model.attn_config.attn_impl=torch (torch attn_impl will be slow). ' + 'Note: (1) requires you have CMake and PyTorch already installed.')
     check_valid_inputs(query, key, value)
+    if multiquery:
+        warnings.warn(DeprecationWarning('The direct use of the multiquery arg is deprecated. Setting kv_n_heads=1 automatically. Please set kv_n_heads=1 explicitly to remove this warning.'))
+        kv_n_heads = 1
+    elif kv_n_heads is None:
+        warnings.warn(DeprecationWarning('Not specifying a value for the kv_n_heads arg is deprecated. Setting kv_n_heads=n_heads automatically. Please set kv_n_heads=n_heads explicitly to remove this warning.'))
+        kv_n_heads = n_heads
     if past_key_value is not None:
         if len(past_key_value) != 0:
             key = torch.cat([past_key_value[0], key], dim=1)
@@ -129,6 +187,7 @@ def triton_flash_attn_fn(query, key, value, n_heads, past_key_value=None, softma
         attn_bias = attn_bias[:, :, _s_q:, _s_k:]
     if dropout_p:
         raise NotImplementedError(f'Dropout not implemented for attn_impl: triton.')
+    dropout_p = dropout_p if training else 0.0
     if needs_weights:
         raise NotImplementedError(f'attn_impl: triton cannot return attn weights.')
     if key_padding_mask is not None:
@@ -138,124 +197,103 @@ def triton_flash_attn_fn(query, key, value, n_heads, past_key_value=None, softma
             attn_bias = query.new_zeros(b_size, 1, 1, s_k)
         attn_bias = attn_bias.masked_fill(~key_padding_mask.view((b_size, 1, 1, s_k)), torch.finfo(query.dtype).min)
     query = rearrange(query, 'b s (h d) -> b s h d', h=n_heads)
-    key = rearrange(key, 'b s (h d) -> b s h d', h=1 if multiquery else n_heads)
-    value = rearrange(value, 'b s (h d) -> b s h d', h=1 if multiquery else n_heads)
-    if multiquery:
-        key = key.expand(*key.shape[:2], n_heads, key.size(-1))
-        value = value.expand(*value.shape[:2], n_heads, value.size(-1))
+    key = rearrange(key, 'b s (h d) -> b s h d', h=kv_n_heads)
+    value = rearrange(value, 'b s (h d) -> b s h d', h=kv_n_heads)
+    if kv_n_heads == 1:
+        key = key.repeat(1, 1, n_heads, 1)
+        value = value.repeat(1, 1, n_heads, 1)
+    elif kv_n_heads < n_heads:
+        key = repeat_kv_for_gqa(key, n_heads // kv_n_heads)
+        value = repeat_kv_for_gqa(value, n_heads // kv_n_heads)
     reset_is_causal = _reset_is_causal(query.size(1), key.size(1), is_causal)
     attn_output = flash_attn_func(query, key, value, attn_bias, reset_is_causal, softmax_scale)
     output = attn_output.view(*attn_output.shape[:2], -1)
     return (output, None, past_key_value)
 
-class MultiheadAttention(nn.Module):
-    """Multi-head self attention.
+class GroupedQueryAttention(nn.Module):
+    """Grouped Query Attention (GQA) is a generalization of Multi-head (MHA).
 
-    Using torch or triton attention implemetation enables user to also use
-    additive bias.
+    and Multi-query attention (MQA).
+
+    This allows the user to set a variable of number of kv_n_heads, rather than
+    just n_heads or 1, as in MHA and MQA. Using torch or triton attention
+    implementation enables user to also use additive bias.
     """
 
-    def __init__(self, d_model: int, n_heads: int, attn_impl: str='triton', clip_qkv: Optional[float]=None, qk_ln: bool=False, softmax_scale: Optional[float]=None, attn_pdrop: float=0.0, low_precision_layernorm: bool=False, verbose: int=0, device: Optional[str]=None):
+    def __init__(self, d_model: int, n_heads: int, kv_n_heads: int, attn_impl: str='triton', clip_qkv: Optional[float]=None, qk_ln: bool=False, softmax_scale: Optional[float]=None, attn_pdrop: float=0.0, norm_type: str='low_precision_layernorm', fc_type: str='torch', device: Optional[str]=None, bias: bool=True):
         super().__init__()
         self.attn_impl = attn_impl
         self.clip_qkv = clip_qkv
         self.qk_ln = qk_ln
         self.d_model = d_model
         self.n_heads = n_heads
+        self.kv_n_heads = kv_n_heads
+        self.head_dim = d_model // n_heads
+        if self.kv_n_heads <= 0:
+            raise ValueError('kv_n_heads should be greater than zero.')
+        if self.kv_n_heads > self.n_heads:
+            raise ValueError('The number of KV heads should be less than or equal to Q heads.')
+        if self.n_heads % self.kv_n_heads != 0:
+            raise ValueError('Each Q head should get the same number of KV heads, so n_heads must be divisible by kv_n_heads.')
         self.softmax_scale = softmax_scale
         if self.softmax_scale is None:
             self.softmax_scale = 1 / math.sqrt(self.d_model / self.n_heads)
         self.attn_dropout_p = attn_pdrop
-        self.Wqkv = nn.Linear(self.d_model, 3 * self.d_model, device=device)
-        fuse_splits = (d_model, 2 * d_model)
+        fc_kwargs: dict[str, Any] = {'bias': bias}
+        if fc_type != 'te':
+            fc_kwargs['device'] = device
+        self.Wqkv = FC_CLASS_REGISTRY[fc_type](self.d_model, self.d_model + 2 * self.kv_n_heads * self.head_dim, **fc_kwargs)
+        fuse_splits = [i * self.head_dim for i in range(1, self.n_heads + 2 * self.kv_n_heads)]
         self.Wqkv._fused = (0, fuse_splits)
         if self.qk_ln:
-            layernorm_class = LPLayerNorm if low_precision_layernorm else nn.LayerNorm
-            self.q_ln = layernorm_class(self.d_model, device=device)
-            self.k_ln = layernorm_class(self.d_model, device=device)
+            norm_class = NORM_CLASS_REGISTRY[norm_type.lower()]
+            self.q_ln = norm_class(self.d_model, device=device)
+            self.k_ln = norm_class(self.kv_n_heads * self.head_dim, device=device)
         if self.attn_impl == 'flash':
             self.attn_fn = flash_attn_fn
         elif self.attn_impl == 'triton':
             self.attn_fn = triton_flash_attn_fn
-            if verbose:
-                warnings.warn('While `attn_impl: triton` can be faster than `attn_impl: flash` ' + 'it uses more memory. When training larger models this can trigger ' + 'alloc retries which hurts performance. If encountered, we recommend ' + 'using `attn_impl: flash` if your model does not use `alibi` or `prefix_lm`.')
         elif self.attn_impl == 'torch':
             self.attn_fn = scaled_multihead_dot_product_attention
-            if torch.cuda.is_available() and verbose:
-                warnings.warn('Using `attn_impl: torch`. If your model does not use `alibi` or ' + '`prefix_lm` we recommend using `attn_impl: flash` otherwise ' + 'we recommend using `attn_impl: triton`.')
         else:
             raise ValueError(f'attn_impl={attn_impl!r} is an invalid setting.')
-        self.out_proj = nn.Linear(self.d_model, self.d_model, device=device)
+        self.out_proj = FC_CLASS_REGISTRY[fc_type](self.d_model, self.d_model, **fc_kwargs)
         self.out_proj._is_residual = True
 
-    def forward(self, x, past_key_value=None, attn_bias=None, attention_mask=None, is_causal=True, needs_weights=False):
+    def forward(self, x: torch.Tensor, past_key_value: Optional[Tuple[torch.Tensor, torch.Tensor]]=None, attn_bias: Optional[torch.Tensor]=None, attention_mask: Optional[torch.Tensor]=None, is_causal: bool=True, needs_weights: bool=False) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor, torch.Tensor]]]:
         qkv = self.Wqkv(x)
         if self.clip_qkv:
-            qkv.clamp_(min=-self.clip_qkv, max=self.clip_qkv)
-        (query, key, value) = qkv.chunk(3, dim=2)
+            qkv = qkv.clamp(min=-self.clip_qkv, max=self.clip_qkv)
+        (query, key, value) = qkv.split([self.d_model, self.kv_n_heads * self.head_dim, self.kv_n_heads * self.head_dim], dim=2)
         key_padding_mask = attention_mask
         if self.qk_ln:
             dtype = query.dtype
             query = self.q_ln(query).to(dtype)
             key = self.k_ln(key).to(dtype)
-        (context, attn_weights, past_key_value) = self.attn_fn(query, key, value, self.n_heads, past_key_value=past_key_value, softmax_scale=self.softmax_scale, attn_bias=attn_bias, key_padding_mask=key_padding_mask, is_causal=is_causal, dropout_p=self.attn_dropout_p, training=self.training, needs_weights=needs_weights)
+        (context, attn_weights, past_key_value) = self.attn_fn(query, key, value, self.n_heads, self.kv_n_heads, past_key_value=past_key_value, softmax_scale=self.softmax_scale, attn_bias=attn_bias, key_padding_mask=key_padding_mask, is_causal=is_causal, dropout_p=self.attn_dropout_p, training=self.training, needs_weights=needs_weights)
         return (self.out_proj(context), attn_weights, past_key_value)
 
-class MultiQueryAttention(nn.Module):
-    """Multi-Query self attention.
+class MultiheadAttention(GroupedQueryAttention):
+    """Multi-head self attention.
 
-    Using torch or triton attention implemetation enables user to also use
+    Using torch or triton attention implementation enables user to also use
     additive bias.
     """
 
-    def __init__(self, d_model: int, n_heads: int, attn_impl: str='triton', clip_qkv: Optional[float]=None, qk_ln: bool=False, softmax_scale: Optional[float]=None, attn_pdrop: float=0.0, low_precision_layernorm: bool=False, verbose: int=0, device: Optional[str]=None):
-        super().__init__()
-        self.attn_impl = attn_impl
-        self.clip_qkv = clip_qkv
-        self.qk_ln = qk_ln
-        self.d_model = d_model
-        self.n_heads = n_heads
-        self.head_dim = d_model // n_heads
-        self.softmax_scale = softmax_scale
-        if self.softmax_scale is None:
-            self.softmax_scale = 1 / math.sqrt(self.head_dim)
-        self.attn_dropout_p = attn_pdrop
-        self.Wqkv = nn.Linear(d_model, d_model + 2 * self.head_dim, device=device)
-        fuse_splits = (d_model, d_model + self.head_dim)
-        self.Wqkv._fused = (0, fuse_splits)
-        if self.qk_ln:
-            layernorm_class = LPLayerNorm if low_precision_layernorm else nn.LayerNorm
-            self.q_ln = layernorm_class(d_model, device=device)
-            self.k_ln = layernorm_class(self.head_dim, device=device)
-        if self.attn_impl == 'flash':
-            self.attn_fn = flash_attn_fn
-        elif self.attn_impl == 'triton':
-            self.attn_fn = triton_flash_attn_fn
-            if verbose:
-                warnings.warn('While `attn_impl: triton` can be faster than `attn_impl: flash` ' + 'it uses more memory. When training larger models this can trigger ' + 'alloc retries which hurts performance. If encountered, we recommend ' + 'using `attn_impl: flash` if your model does not use `alibi` or `prefix_lm`.')
-        elif self.attn_impl == 'torch':
-            self.attn_fn = scaled_multihead_dot_product_attention
-            if torch.cuda.is_available() and verbose:
-                warnings.warn('Using `attn_impl: torch`. If your model does not use `alibi` or ' + '`prefix_lm` we recommend using `attn_impl: flash` otherwise ' + 'we recommend using `attn_impl: triton`.')
-        else:
-            raise ValueError(f'attn_impl={attn_impl!r} is an invalid setting.')
-        self.out_proj = nn.Linear(self.d_model, self.d_model, device=device)
-        self.out_proj._is_residual = True
+    def __init__(self, d_model: int, n_heads: int, attn_impl: str='triton', clip_qkv: Optional[float]=None, qk_ln: bool=False, softmax_scale: Optional[float]=None, attn_pdrop: float=0.0, norm_type: str='low_precision_layernorm', fc_type: str='torch', device: Optional[str]=None, bias: bool=True):
+        super().__init__(d_model=d_model, n_heads=n_heads, kv_n_heads=n_heads, attn_impl=attn_impl, clip_qkv=clip_qkv, qk_ln=qk_ln, softmax_scale=softmax_scale, attn_pdrop=attn_pdrop, norm_type=norm_type, fc_type=fc_type, device=device, bias=bias)
 
-    def forward(self, x, past_key_value=None, attn_bias=None, attention_mask=None, is_causal=True, needs_weights=False):
-        qkv = self.Wqkv(x)
-        if self.clip_qkv:
-            qkv.clamp_(min=-self.clip_qkv, max=self.clip_qkv)
-        (query, key, value) = qkv.split([self.d_model, self.head_dim, self.head_dim], dim=2)
-        key_padding_mask = attention_mask
-        if self.qk_ln:
-            dtype = query.dtype
-            query = self.q_ln(query).to(dtype)
-            key = self.k_ln(key).to(dtype)
-        (context, attn_weights, past_key_value) = self.attn_fn(query, key, value, self.n_heads, past_key_value=past_key_value, softmax_scale=self.softmax_scale, attn_bias=attn_bias, key_padding_mask=key_padding_mask, is_causal=is_causal, dropout_p=self.attn_dropout_p, training=self.training, needs_weights=needs_weights, multiquery=True)
-        return (self.out_proj(context), attn_weights, past_key_value)
+class MultiQueryAttention(GroupedQueryAttention):
+    """Multi-Query self attention.
+
+    Using torch or triton attention implementation enables user to also use
+    additive bias.
+    """
+
+    def __init__(self, d_model: int, n_heads: int, attn_impl: str='triton', clip_qkv: Optional[float]=None, qk_ln: bool=False, softmax_scale: Optional[float]=None, attn_pdrop: float=0.0, norm_type: str='low_precision_layernorm', fc_type: str='torch', device: Optional[str]=None, bias: bool=True):
+        super().__init__(d_model=d_model, n_heads=n_heads, kv_n_heads=1, attn_impl=attn_impl, clip_qkv=clip_qkv, qk_ln=qk_ln, softmax_scale=softmax_scale, attn_pdrop=attn_pdrop, norm_type=norm_type, fc_type=fc_type, device=device, bias=bias)
 
-def attn_bias_shape(attn_impl, n_heads, seq_len, alibi, prefix_lm, causal, use_sequence_id):
+def attn_bias_shape(attn_impl: str, n_heads: int, seq_len: int, alibi: bool, prefix_lm: bool, causal: bool, use_sequence_id: bool) -> Optional[Tuple[int, int, int, int]]:
     if attn_impl == 'flash':
         return None
     elif attn_impl in ['torch', 'triton']:
@@ -269,7 +307,7 @@ def attn_bias_shape(attn_impl, n_heads, seq_len, alibi, prefix_lm, causal, use_s
     else:
         raise ValueError(f'attn_impl={attn_impl!r} is an invalid setting.')
 
-def build_attn_bias(attn_impl, attn_bias, n_heads, seq_len, causal=False, alibi=False, alibi_bias_max=8):
+def build_attn_bias(attn_impl: str, attn_bias: torch.Tensor, n_heads: int, seq_len: int, causal: bool=False, alibi: bool=False, alibi_bias_max: int=8) -> Optional[torch.Tensor]:
     if attn_impl == 'flash':
         return None
     elif attn_impl in ['torch', 'triton']:
@@ -280,7 +318,7 @@ def build_attn_bias(attn_impl, attn_bias, n_heads, seq_len, causal=False, alibi=
     else:
         raise ValueError(f'attn_impl={attn_impl!r} is an invalid setting.')
 
-def gen_slopes(n_heads, alibi_bias_max=8, device=None):
+def gen_slopes(n_heads: int, alibi_bias_max: int=8, device: Optional[torch.device]=None) -> torch.Tensor:
     _n_heads = 2 ** math.ceil(math.log2(n_heads))
     m = torch.arange(1, _n_heads + 1, dtype=torch.float32, device=device)
     m = m.mul(alibi_bias_max / _n_heads)
@@ -289,7 +327,7 @@ def gen_slopes(n_heads, alibi_bias_max=8, device=None):
         slopes = torch.concat([slopes[1::2], slopes[::2]])[:n_heads]
     return slopes.view(1, n_heads, 1, 1)
 
-def build_alibi_bias(n_heads, seq_len, full=False, alibi_bias_max=8, device=None, dtype=None):
+def build_alibi_bias(n_heads: int, seq_len: int, full: bool=False, alibi_bias_max: int=8, device: Optional[torch.device]=None, dtype: Optional[torch.dtype]=None) -> torch.Tensor:
     alibi_bias = torch.arange(1 - seq_len, 1, dtype=torch.int32, device=device).view(1, 1, 1, seq_len)
     if full:
         alibi_bias = alibi_bias - torch.arange(1 - seq_len, 1, dtype=torch.int32, device=device).view(1, 1, seq_len, 1)
@@ -297,4 +335,4 @@ def build_alibi_bias(n_heads, seq_len, full=False, alibi_bias_max=8, device=None
     slopes = gen_slopes(n_heads, alibi_bias_max, device=device)
     alibi_bias = alibi_bias * slopes
     return alibi_bias.to(dtype=dtype)
-ATTN_CLASS_REGISTRY = {'multihead_attention': MultiheadAttention, 'multiquery_attention': MultiQueryAttention}
+ATTN_CLASS_REGISTRY = {'multihead_attention': MultiheadAttention, 'multiquery_attention': MultiQueryAttention, 'grouped_query_attention': GroupedQueryAttention}

blocks.py

@@ -1,41 +1,41 @@
 """GPT Blocks used for the GPT Model."""
-from typing import Dict, Optional, Tuple
+from typing import Any, Dict, Optional, Tuple
 import torch
 import torch.nn as nn
 from .attention import ATTN_CLASS_REGISTRY
+from .ffn import FFN_CLASS_REGISTRY, build_ffn
 from .norm import NORM_CLASS_REGISTRY
 
-class MPTMLP(nn.Module):
-
-    def __init__(self, d_model: int, expansion_ratio: int, device: Optional[str]=None):
-        super().__init__()
-        self.up_proj = nn.Linear(d_model, expansion_ratio * d_model, device=device)
-        self.act = nn.GELU(approximate='none')
-        self.down_proj = nn.Linear(expansion_ratio * d_model, d_model, device=device)
-        self.down_proj._is_residual = True
-
-    def forward(self, x):
-        return self.down_proj(self.act(self.up_proj(x)))
-
 class MPTBlock(nn.Module):
 
-    def __init__(self, d_model: int, n_heads: int, expansion_ratio: int, attn_config: Dict={'attn_type': 'multihead_attention', 'attn_pdrop': 0.0, 'attn_impl': 'triton', 'qk_ln': False, 'clip_qkv': None, 'softmax_scale': None, 'prefix_lm': False, 'attn_uses_sequence_id': False, 'alibi': False, 'alibi_bias_max': 8}, resid_pdrop: float=0.0, norm_type: str='low_precision_layernorm', verbose: int=0, device: Optional[str]=None, **kwargs):
+    def __init__(self, d_model: int, n_heads: int, expansion_ratio: int, attn_config: Optional[Dict]=None, ffn_config: Optional[Dict]=None, resid_pdrop: float=0.0, norm_type: str='low_precision_layernorm', fc_type: str='torch', device: Optional[str]=None, no_bias: bool=False, **kwargs: Any):
+        if attn_config is None:
+            attn_config = {'attn_type': 'multihead_attention', 'attn_pdrop': 0.0, 'attn_impl': 'triton', 'qk_ln': False, 'clip_qkv': None, 'softmax_scale': None, 'prefix_lm': False, 'attn_uses_sequence_id': False, 'alibi': False, 'alibi_bias_max': 8}
+        if ffn_config is None:
+            ffn_config = {'ffn_type': 'mptmlp'}
         del kwargs
         super().__init__()
         norm_class = NORM_CLASS_REGISTRY[norm_type.lower()]
+        assert isinstance(attn_config['attn_type'], str)
         attn_class = ATTN_CLASS_REGISTRY[attn_config['attn_type']]
+        args_to_exclude_in_attn_class = {'attn_type', 'prefix_lm', 'alibi', 'attn_uses_sequence_id', 'alibi_bias_max'}
+        attn_config_subset_for_attn_class = {k: v for (k, v) in attn_config.items() if k not in args_to_exclude_in_attn_class}
         self.norm_1 = norm_class(d_model, device=device)
-        self.attn = attn_class(attn_impl=attn_config['attn_impl'], clip_qkv=attn_config['clip_qkv'], qk_ln=attn_config['qk_ln'], softmax_scale=attn_config['softmax_scale'], attn_pdrop=attn_config['attn_pdrop'], d_model=d_model, n_heads=n_heads, verbose=verbose, device=device)
-        self.norm_2 = norm_class(d_model, device=device)
-        self.ffn = MPTMLP(d_model=d_model, expansion_ratio=expansion_ratio, device=device)
+        self.attn = attn_class(d_model=d_model, n_heads=n_heads, fc_type=fc_type, device=device, **attn_config_subset_for_attn_class, bias=not no_bias)
+        self.norm_2 = None
+        if not getattr(FFN_CLASS_REGISTRY[ffn_config['ffn_type']], '_has_norm', False):
+            self.norm_2 = norm_class(d_model, device=device)
+        self.ffn = build_ffn(d_model=d_model, expansion_ratio=expansion_ratio, device=device, bias=not no_bias, **ffn_config)
         self.resid_attn_dropout = nn.Dropout(resid_pdrop)
         self.resid_ffn_dropout = nn.Dropout(resid_pdrop)
 
-    def forward(self, x: torch.Tensor, past_key_value: Optional[Tuple[torch.Tensor]]=None, attn_bias: Optional[torch.Tensor]=None, attention_mask: Optional[torch.ByteTensor]=None, is_causal: bool=True) -> Tuple[torch.Tensor, Optional[Tuple[torch.Tensor]]]:
+    def forward(self, x: torch.Tensor, past_key_value: Optional[Tuple[torch.Tensor, torch.Tensor]]=None, attn_bias: Optional[torch.Tensor]=None, attention_mask: Optional[torch.ByteTensor]=None, is_causal: bool=True, output_attentions: bool=False) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor, torch.Tensor]]]:
         a = self.norm_1(x)
-        (b, attn_weights, past_key_value) = self.attn(a, past_key_value=past_key_value, attn_bias=attn_bias, attention_mask=attention_mask, is_causal=is_causal)
+        (b, attn_weights, past_key_value) = self.attn(a, past_key_value=past_key_value, attn_bias=attn_bias, attention_mask=attention_mask, is_causal=is_causal, needs_weights=output_attentions)
         x = x + self.resid_attn_dropout(b)
-        m = self.norm_2(x)
+        m = x
+        if self.norm_2 is not None:
+            m = self.norm_2(x)
         n = self.ffn(m)
         x = x + self.resid_ffn_dropout(n)
         return (x, attn_weights, past_key_value)

configuration_mpt.py

@@ -1,27 +1,29 @@
 """A HuggingFace-style model configuration."""
-from typing import Dict, Optional, Union
+import warnings
+from typing import Any, Dict, Optional, Union
 from transformers import PretrainedConfig
 attn_config_defaults: Dict = {'attn_type': 'multihead_attention', 'attn_pdrop': 0.0, 'attn_impl': 'triton', 'qk_ln': False, 'clip_qkv': None, 'softmax_scale': None, 'prefix_lm': False, 'attn_uses_sequence_id': False, 'alibi': False, 'alibi_bias_max': 8}
+ffn_config_defaults: Dict = {'ffn_type': 'mptmlp'}
 init_config_defaults: Dict = {'name': 'kaiming_normal_', 'fan_mode': 'fan_in', 'init_nonlinearity': 'relu', 'init_div_is_residual': True, 'emb_init_std': None, 'emb_init_uniform_lim': None, 'init_std': None, 'init_gain': 0.0}
 
 class MPTConfig(PretrainedConfig):
     model_type = 'mpt'
 
-    def __init__(self, d_model: int=2048, n_heads: int=16, n_layers: int=24, expansion_ratio: int=4, max_seq_len: int=2048, vocab_size: int=50368, resid_pdrop: float=0.0, emb_pdrop: float=0.0, learned_pos_emb: bool=True, attn_config: Dict=attn_config_defaults, init_device: str='cpu', logit_scale: Optional[Union[float, str]]=None, no_bias: bool=False, verbose: int=0, embedding_fraction: float=1.0, norm_type: str='low_precision_layernorm', use_cache: bool=False, init_config: Dict=init_config_defaults, **kwargs):
+    def __init__(self, d_model: int=2048, n_heads: int=16, n_layers: int=24, expansion_ratio: int=4, max_seq_len: int=2048, vocab_size: int=50368, resid_pdrop: float=0.0, emb_pdrop: float=0.0, learned_pos_emb: bool=True, attn_config: Dict=attn_config_defaults, ffn_config: Dict=ffn_config_defaults, init_device: str='cpu', logit_scale: Optional[Union[float, str]]=None, no_bias: bool=False, embedding_fraction: float=1.0, norm_type: str='low_precision_layernorm', use_cache: bool=False, init_config: Dict=init_config_defaults, fc_type: str='torch', verbose: Optional[int]=None, **kwargs: Any):
         """The MPT configuration class.
 
         Args:
             d_model (int): The size of the embedding dimension of the model.
             n_heads (int): The number of attention heads.
             n_layers (int): The number of layers in the model.
-            expansion_ratio (int): The ratio of the up/down scale in the MLP.
+            expansion_ratio (int): The ratio of the up/down scale in the ffn.
             max_seq_len (int): The maximum sequence length of the model.
             vocab_size (int): The size of the vocabulary.
             resid_pdrop (float): The dropout probability applied to the attention output before combining with residual.
             emb_pdrop (float): The dropout probability for the embedding layer.
             learned_pos_emb (bool): Whether to use learned positional embeddings
-            attn_config (Dict):  A dictionary used to configure the model's attention module:
-                attn_type (str): type of attention to use. Options: multihead_attention, multiquery_attention
+            attn_config (Dict): A dictionary used to configure the model's attention module:
+                attn_type (str): type of attention to use. Options: multihead_attention, multiquery_attention, grouped_query_attention
                 attn_pdrop (float): The dropout probability for the attention layers.
                 attn_impl (str): The attention implementation to use. One of 'torch', 'flash', or 'triton'.
                 qk_ln (bool): Whether to apply layer normalization to the queries and keys in the attention layer.
@@ -38,13 +40,15 @@ class MPTConfig(PretrainedConfig):
                     Defaults to ``False`` meaning any provided `sequence_id` will be ignored.
                 alibi (bool): Whether to use the alibi bias instead of position embeddings.
                 alibi_bias_max (int): The maximum value of the alibi bias.
+                kv_n_heads (Optional[int]): For grouped_query_attention only, allow user to specify number of kv heads.
+            ffn_config (Dict): A dictionary used to configure the model's ffn module:
+                ffn_type (str): type of ffn to use. Options: mptmlp, te_ln_mlp
             init_device (str): The device to use for parameter initialization.
             logit_scale (Optional[Union[float, str]]): If not None, scale the logits by this value.
             no_bias (bool): Whether to use bias in all layers.
             verbose (int): The verbosity level. 0 is silent.
             embedding_fraction (float): The fraction to scale the gradients of the embedding layer by.
             norm_type (str): choose type of norm to use
-            multiquery_attention (bool): Whether to use multiquery attention implementation.
             use_cache (bool): Whether or not the model should return the last key/values attentions
             init_config (Dict): A dictionary used to configure the model initialization:
                 init_config.name: The parameter initialization scheme to use. Options: 'default_', 'baseline_',
@@ -61,6 +65,7 @@ class MPTConfig(PretrainedConfig):
                 init_nonlinearity (str): The nonlinearity to use for parameter initialization with kaiming initialization schemes.
                 ---
                 See llmfoundry.models.utils.param_init_fns.py for info on other param init config options
+            fc_type (str): choose fc layer implementation. Options: torch and te. te layers support fp8 when using H100 GPUs.
         """
         self.d_model = d_model
         self.n_heads = n_heads
@@ -72,29 +77,36 @@ class MPTConfig(PretrainedConfig):
         self.emb_pdrop = emb_pdrop
         self.learned_pos_emb = learned_pos_emb
         self.attn_config = attn_config
+        self.ffn_config = ffn_config
         self.init_device = init_device
         self.logit_scale = logit_scale
         self.no_bias = no_bias
-        self.verbose = verbose
         self.embedding_fraction = embedding_fraction
         self.norm_type = norm_type
         self.use_cache = use_cache
         self.init_config = init_config
+        self.fc_type = fc_type
+        if verbose is not None:
+            warnings.warn(DeprecationWarning('verbose argument for MPTConfig is now ignored and will be removed. Use python_log_level instead.'))
         if 'name' in kwargs:
             del kwargs['name']
         if 'loss_fn' in kwargs:
             del kwargs['loss_fn']
+        if self.attn_config.get('alibi', False):
+            self.learned_pos_emb = False
+            warnings.warn(f'alibi is turned on, setting `learned_pos_emb` to `False.`')
         super().__init__(**kwargs)
         self._validate_config()
 
-    def _set_config_defaults(self, config, config_defaults):
+    def _set_config_defaults(self, config: Dict[str, Any], config_defaults: Dict[str, Any]) -> Dict[str, Any]:
         for (k, v) in config_defaults.items():
             if k not in config:
                 config[k] = v
         return config
 
-    def _validate_config(self):
+    def _validate_config(self) -> None:
         self.attn_config = self._set_config_defaults(self.attn_config, attn_config_defaults)
+        self.ffn_config = self._set_config_defaults(self.ffn_config, ffn_config_defaults)
         self.init_config = self._set_config_defaults(self.init_config, init_config_defaults)
         if self.d_model % self.n_heads != 0:
             raise ValueError('d_model must be divisible by n_heads')
@@ -115,4 +127,14 @@ class MPTConfig(PretrainedConfig):
         if self.init_config.get('name', None) is None:
             raise ValueError(f"self.init_config={self.init_config!r} 'name' needs to be set.")
         if not self.learned_pos_emb and (not self.attn_config['alibi']):
-            raise ValueError(f'Positional information must be provided to the model using either learned_pos_emb or alibi.')
+            warnings.warn(f'Positional information not being provided to the model using either learned_pos_emb or alibi.')
+        if self.fc_type == 'te' or self.ffn_config['ffn_type'] == 'te_ln_mlp':
+            try:
+                import transformer_engine.pytorch as te
+                del te
+            except:
+                raise ImportError('TransformerEngine import fail. `fc_type: te` requires TransformerEngine be installed. ' + 'The required version of transformer_engine also requires FlashAttention v1.0.6 is installed:\n' + 'pip install flash-attn==1.0.6 --no-build-isolation \n' + 'pip install git+https://github.com/NVIDIA/TransformerEngine.git@144e4888b2cdd60bd52e706d5b7a79cb9c1a7156')
+        if self.ffn_config['ffn_type'] == 'mptmlp':
+            self.ffn_config['fc_type'] = self.fc_type
+        elif self.ffn_config['ffn_type'] == 'te_ln_mlp':
+            self.ffn_config['bias'] = not self.no_bias

custom_embedding.py

@@ -1,4 +1,3 @@
-import torch
 import torch.nn as nn
 import torch.nn.functional as F
 from torch import Tensor

fc.py

@@ -0,0 +1,7 @@
+from torch import nn
+FC_CLASS_REGISTRY = {'torch': nn.Linear}
+try:
+    import transformer_engine.pytorch as te
+    FC_CLASS_REGISTRY['te'] = te.Linear
+except:
+    pass

ffn.py

@@ -0,0 +1,39 @@
+"""GPT Blocks used for the GPT Model."""
+from typing import Any, Optional
+import torch
+import torch.nn as nn
+from .fc import FC_CLASS_REGISTRY
+try:
+    import transformer_engine.pytorch as te
+except:
+    te = None
+
+class MPTMLP(nn.Module):
+
+    def __init__(self, d_model: int, expansion_ratio: int, fc_type: str='torch', device: Optional[str]=None, bias: bool=True):
+        super().__init__()
+        fc_kwargs: dict[str, Any] = {'bias': bias}
+        if fc_type != 'te':
+            fc_kwargs['device'] = device
+        self.up_proj = FC_CLASS_REGISTRY[fc_type](d_model, expansion_ratio * d_model, **fc_kwargs)
+        self.act = nn.GELU(approximate='none')
+        self.down_proj = FC_CLASS_REGISTRY[fc_type](expansion_ratio * d_model, d_model, **fc_kwargs)
+        self.down_proj._is_residual = True
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.down_proj(self.act(self.up_proj(x)))
+FFN_CLASS_REGISTRY = {'mptmlp': MPTMLP}
+if te is not None:
+    te.LayerNormMLP._has_norm = True
+    FFN_CLASS_REGISTRY['te_ln_mlp'] = te.LayerNormMLP
+
+def build_ffn(d_model: int, expansion_ratio: int, fc_type: str='torch', device: Optional[str]=None, bias: bool=True, **kwargs: Any) -> nn.Module:
+    ffn_type = kwargs.pop('ffn_type')
+    if ffn_type == 'mptmlp':
+        if len(kwargs) > 0:
+            raise ValueError(f'MPTMLP got an unexpected keyword argument: {kwargs}')
+        return MPTMLP(d_model=d_model, expansion_ratio=expansion_ratio, fc_type=fc_type, device=device, bias=bias)
+    elif ffn_type == 'te_ln_mlp':
+        assert te is not None
+        return te.LayerNormMLP(hidden_size=d_model, ffn_hidden_size=d_model * expansion_ratio, bias=bias, **kwargs)
+    raise ValueError(f'ffn_type={ffn_type!r} not recognized.')

hf_prefixlm_converter.py

@@ -9,7 +9,7 @@ and treat the input prompt as the prefix in `generate`.
 import math
 import warnings
 from types import MethodType
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Any, List, MutableMapping, Optional, Tuple, Union
 import torch
 from transformers.models.bloom.modeling_bloom import BaseModelOutputWithPastAndCrossAttentions, BloomForCausalLM, BloomModel, CausalLMOutputWithCrossAttentions, CrossEntropyLoss
 from transformers.models.bloom.modeling_bloom import _expand_mask as _expand_mask_bloom
@@ -90,13 +90,14 @@ def _convert_gpt_causal_lm_to_prefix_lm(model: CAUSAL_GPT_TYPES) -> CAUSAL_GPT_T
             bidirectional_mask = torch.cat([bidirectional_mask, pad], dim=1)
         bidirectional = bidirectional_mask.unsqueeze(1).unsqueeze(1)
         for attn_module in attn_modules:
+            assert isinstance(attn_module.bias, torch.Tensor)
             attn_module.bias.data = torch.logical_or(attn_module.bias.data, bidirectional)
         output = call_og_forward()
         for attn_module in attn_modules:
             attn_module.bias.data = torch.tril(attn_module.bias.data[0, 0])[None, None]
         return output
 
-    def generate(self: CAUSAL_GPT_TYPES, *args: tuple, **kwargs: Dict[str, Any]):
+    def generate(self: CAUSAL_GPT_TYPES, *args: Any, **kwargs: Any):
         """Wraps original generate to enable PrefixLM attention."""
         attn_modules = _get_attn_modules(model)
         for attn_module in attn_modules:
@@ -157,7 +158,7 @@ def _convert_bloom_causal_lm_to_prefix_lm(model: BloomForCausalLM) -> BloomForCa
         return alibi.to(dtype)
     KeyValueT = Tuple[torch.Tensor, torch.Tensor]
 
-    def forward(self: BloomModel, input_ids: Optional[torch.LongTensor]=None, past_key_values: Optional[Tuple[KeyValueT, ...]]=None, attention_mask: Optional[torch.Tensor]=None, bidirectional_mask: Optional[torch.Tensor]=None, head_mask: Optional[torch.LongTensor]=None, inputs_embeds: Optional[torch.LongTensor]=None, use_cache: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, return_dict: Optional[bool]=None, **deprecated_arguments) -> Union[Tuple[torch.Tensor, ...], BaseModelOutputWithPastAndCrossAttentions]:
+    def transformer_forward(self: BloomModel, input_ids: Optional[torch.LongTensor]=None, past_key_values: Optional[Tuple[KeyValueT, ...]]=None, attention_mask: Optional[torch.Tensor]=None, bidirectional_mask: Optional[torch.Tensor]=None, head_mask: Optional[torch.LongTensor]=None, inputs_embeds: Optional[torch.LongTensor]=None, use_cache: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, return_dict: Optional[bool]=None, **deprecated_arguments: Any) -> Union[Tuple[torch.Tensor, ...], BaseModelOutputWithPastAndCrossAttentions]:
         if deprecated_arguments.pop('position_ids', False) is not False:
             warnings.warn('`position_ids` have no functionality in BLOOM and will be removed in v5.0.0. ' + 'You can safely ignore passing `position_ids`.', FutureWarning)
         if len(deprecated_arguments) > 0:
@@ -204,9 +205,9 @@ def _convert_bloom_causal_lm_to_prefix_lm(model: BloomForCausalLM) -> BloomForCa
                     logger.warning('`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...')
                     use_cache = False
 
-                def create_custom_forward(module):
+                def create_custom_forward(module: torch.nn.Module):
 
-                    def custom_forward(*inputs):
+                    def custom_forward(*inputs: Any):
                         return module(*inputs, use_cache=use_cache, output_attentions=output_attentions)
                     return custom_forward
                 outputs = torch.utils.checkpoint.checkpoint(create_custom_forward(block), hidden_states, alibi, causal_mask, head_mask[i])
@@ -227,10 +228,10 @@ def _convert_bloom_causal_lm_to_prefix_lm(model: BloomForCausalLM) -> BloomForCa
         return BaseModelOutputWithPastAndCrossAttentions(last_hidden_state=hidden_states, past_key_values=presents, hidden_states=all_hidden_states, attentions=all_self_attentions)
     setattr(model.transformer, '_prepare_attn_mask', MethodType(_prepare_attn_mask, model.transformer))
     setattr(model.transformer, '_build_alibi_tensor', MethodType(_build_alibi_tensor, model.transformer))
-    setattr(model.transformer, 'forward', MethodType(forward, model.transformer))
+    setattr(model.transformer, 'forward', MethodType(transformer_forward, model.transformer))
     KeyValueT = Tuple[torch.Tensor, torch.Tensor]
 
-    def forward(self: BloomForCausalLM, input_ids: Optional[torch.LongTensor]=None, past_key_values: Optional[Tuple[KeyValueT, ...]]=None, attention_mask: Optional[torch.Tensor]=None, bidirectional_mask: Optional[torch.Tensor]=None, head_mask: Optional[torch.Tensor]=None, inputs_embeds: Optional[torch.Tensor]=None, labels: Optional[torch.Tensor]=None, use_cache: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, return_dict: Optional[bool]=None, **deprecated_arguments) -> Union[Tuple[torch.Tensor], CausalLMOutputWithCrossAttentions]:
+    def forward(self: BloomForCausalLM, input_ids: Optional[torch.LongTensor]=None, past_key_values: Optional[Tuple[KeyValueT, ...]]=None, attention_mask: Optional[torch.Tensor]=None, bidirectional_mask: Optional[torch.Tensor]=None, head_mask: Optional[torch.Tensor]=None, inputs_embeds: Optional[torch.Tensor]=None, labels: Optional[torch.Tensor]=None, use_cache: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, return_dict: Optional[bool]=None, **deprecated_arguments: Any) -> Union[Tuple[torch.Tensor], CausalLMOutputWithCrossAttentions]:
         """Replacement forward method for BloomCausalLM."""
         if deprecated_arguments.pop('position_ids', False) is not False:
             warnings.warn('`position_ids` have no functionality in BLOOM and will be removed ' + 'in v5.0.0. You can safely ignore passing `position_ids`.', FutureWarning)
@@ -252,7 +253,8 @@ def _convert_bloom_causal_lm_to_prefix_lm(model: BloomForCausalLM) -> BloomForCa
             return (loss,) + output if loss is not None else output
         return CausalLMOutputWithCrossAttentions(loss=loss, logits=lm_logits, past_key_values=transformer_outputs.past_key_values, hidden_states=transformer_outputs.hidden_states, attentions=transformer_outputs.attentions)
 
-    def prepare_inputs_for_generation(self: BloomForCausalLM, input_ids: torch.LongTensor, past: Optional[torch.Tensor]=None, attention_mask: Optional[torch.Tensor]=None, **kwargs) -> dict:
+    def prepare_inputs_for_generation(self: BloomForCausalLM, input_ids: torch.LongTensor, past: Optional[torch.Tensor]=None, attention_mask: Optional[torch.Tensor]=None, **kwargs: Any) -> dict:
+        del kwargs
         if past:
             input_ids = input_ids[:, -1].unsqueeze(-1)
             bidirectional_mask = None
@@ -282,19 +284,22 @@ def _convert_opt_causal_lm_to_prefix_lm(model: OPTForCausalLM) -> OPTForCausalLM
     setattr(model, '_original_generate', getattr(model, 'generate'))
     model.model.decoder.bidirectional_mask = None
 
-    def _prepare_decoder_attention_mask(self, attention_mask, input_shape, inputs_embeds, past_key_values_length):
+    def _prepare_decoder_attention_mask(self: torch.nn.Module, attention_mask: Optional[torch.Tensor], input_shape: Tuple[int, int], inputs_embeds: Optional[torch.Tensor], past_key_values_length: int):
         combined_attention_mask = None
         if input_shape[-1] > 1:
+            assert inputs_embeds is not None
             if self.bidirectional_mask == 'g':
                 (bsz, src_length) = input_shape
                 combined_attention_mask = torch.zeros((bsz, 1, src_length, src_length + past_key_values_length), dtype=inputs_embeds.dtype, device=inputs_embeds.device)
             else:
                 combined_attention_mask = _make_causal_mask_opt(input_shape, inputs_embeds.dtype, past_key_values_length=past_key_values_length).to(inputs_embeds.device)
                 if self.bidirectional_mask is not None:
+                    assert attention_mask is not None
                     assert attention_mask.shape == self.bidirectional_mask.shape
                     expanded_bidirectional_mask = _expand_mask_opt(self.bidirectional_mask, inputs_embeds.dtype, tgt_len=input_shape[-1]).to(inputs_embeds.device)
                     combined_attention_mask = torch.maximum(expanded_bidirectional_mask, combined_attention_mask)
         if attention_mask is not None:
+            assert inputs_embeds is not None
             expanded_attn_mask = _expand_mask_opt(attention_mask, inputs_embeds.dtype, tgt_len=input_shape[-1]).to(inputs_embeds.device)
             combined_attention_mask = expanded_attn_mask if combined_attention_mask is None else expanded_attn_mask + combined_attention_mask
         return combined_attention_mask
@@ -315,7 +320,7 @@ def _convert_opt_causal_lm_to_prefix_lm(model: OPTForCausalLM) -> OPTForCausalLM
         self.model.decoder.bidirectional_mask = None
         return outputs
 
-    def generate(self: OPTForCausalLM, *args: tuple, **kwargs: Dict[str, Any]):
+    def generate(self: OPTForCausalLM, *args: tuple, **kwargs: Any):
         """Wraps original generate to enable PrefixLM-style attention."""
         self.model.decoder.bidirectional_mask = 'g'
         try:
@@ -398,7 +403,7 @@ def convert_hf_causal_lm_to_prefix_lm(model: CAUSAL_LM_TYPES) -> CAUSAL_LM_TYPES
     else:
         raise TypeError(f'Cannot convert model to Prefix LM. ' + f'Model does not belong to set of supported HF models:' + f'\n{_SUPPORTED_HF_MODELS}')
 
-def add_bidirectional_mask_if_missing(batch: Dict[str, Any]):
+def add_bidirectional_mask_if_missing(batch: MutableMapping):
     """Attempts to add bidirectional_mask to batch if missing.
 
     Raises:

meta_init_context.py

@@ -1,4 +1,5 @@
 from contextlib import contextmanager
+from typing import Any, Callable, Optional
 import torch
 import torch.nn as nn
 
@@ -57,25 +58,29 @@ def init_on_device(device: torch.device, include_buffers: bool=False):
     if include_buffers:
         old_register_buffer = nn.Module.register_buffer
 
-    def register_empty_parameter(module, name, param):
-        old_register_parameter(module, name, param)
+    def register_empty_parameter(self: torch.nn.Module, name: str, param: Optional[torch.nn.Parameter]):
+        old_register_parameter(self, name, param)
         if param is not None:
-            param_cls = type(module._parameters[name])
-            kwargs = module._parameters[name].__dict__
-            module._parameters[name] = param_cls(module._parameters[name].to(device), **kwargs)
-
-    def register_empty_buffer(module, name, buffer):
-        old_register_buffer(module, name, buffer)
-        if buffer is not None:
-            module._buffers[name] = module._buffers[name].to(device)
+            parameter = self._parameters[name]
+            assert parameter is not None
+            param_cls = type(parameter)
+            kwargs = parameter.__dict__
+            self._parameters[name] = param_cls(parameter.to(device), **kwargs)
+
+    def register_empty_buffer(self: torch.nn.Module, name: str, tensor: Optional[torch.Tensor], persistent: bool=True):
+        old_register_buffer(self, name, tensor, persistent=persistent)
+        if tensor is not None:
+            named_buffer = self._buffers[name]
+            assert named_buffer is not None
+            self._buffers[name] = named_buffer.to(device)
     if include_buffers:
         tensor_constructors_to_patch = {torch_function_name: getattr(torch, torch_function_name) for torch_function_name in ['empty', 'zeros', 'ones', 'full']}
     else:
         tensor_constructors_to_patch = {}
 
-    def patch_tensor_constructor(fn):
+    def patch_tensor_constructor(fn: Callable):
 
-        def wrapper(*args, **kwargs):
+        def wrapper(*args: Any, **kwargs: Any):
             kwargs['device'] = device
             return fn(*args, **kwargs)
         return wrapper

modeling_mpt.py

@@ -4,26 +4,31 @@ Inspired by https://github.com/karpathy/minGPT/blob/master/mingpt/model.py
 """
 import math
 import warnings
-from typing import List, Optional, Tuple, Union
+from typing import Any, Dict, List, Mapping, MutableMapping, Optional, Tuple, Union
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
-from transformers import PreTrainedModel, PreTrainedTokenizer, PreTrainedTokenizerFast
+from transformers import PreTrainedModel, PreTrainedTokenizerBase
 from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast
 from .attention import attn_bias_shape, build_attn_bias
 from .blocks import MPTBlock
 from .custom_embedding import SharedEmbedding
+from .fc import FC_CLASS_REGISTRY as FC_CLASS_REGISTRY
+from .ffn import FFN_CLASS_REGISTRY as FFN_CLASS_REGISTRY
+from .ffn import MPTMLP as MPTMLP
+from .ffn import build_ffn as build_ffn
 from .norm import NORM_CLASS_REGISTRY
 from .configuration_mpt import MPTConfig
 from .adapt_tokenizer import AutoTokenizerForMOD, adapt_tokenizer_for_denoising
 from .hf_prefixlm_converter import add_bidirectional_mask_if_missing, convert_hf_causal_lm_to_prefix_lm
 from .meta_init_context import init_empty_weights
-from .param_init_fns import MODEL_INIT_REGISTRY, generic_param_init_fn_
+from .param_init_fns import generic_param_init_fn_, MODEL_INIT_REGISTRY
 try:
-    from .flash_attn_triton import flash_attn_func
+    from .flash_attn_triton import flash_attn_func as flash_attn_func
 except:
     pass
-Tokenizer = Union[PreTrainedTokenizer, PreTrainedTokenizerFast]
+import logging
+log = logging.getLogger(__name__)
 
 class MPTPreTrainedModel(PreTrainedModel):
     config_class = MPTConfig
@@ -40,6 +45,7 @@ class MPTModel(MPTPreTrainedModel):
         self.attn_uses_sequence_id = config.attn_config['attn_uses_sequence_id']
         self.alibi = config.attn_config['alibi']
         self.alibi_bias_max = config.attn_config['alibi_bias_max']
+        self.learned_pos_emb = config.learned_pos_emb
         if config.init_device == 'mixed':
             if dist.get_local_rank() == 0:
                 config.init_device = 'cpu'
@@ -51,13 +57,13 @@ class MPTModel(MPTPreTrainedModel):
         norm_class = NORM_CLASS_REGISTRY[config.norm_type.lower()]
         self.embedding_fraction = config.embedding_fraction
         self.wte = SharedEmbedding(config.vocab_size, config.d_model, device=config.init_device)
-        if not self.alibi:
+        if self.learned_pos_emb:
             self.wpe = torch.nn.Embedding(config.max_seq_len, config.d_model, device=config.init_device)
         self.emb_drop = nn.Dropout(config.emb_pdrop)
         self.blocks = nn.ModuleList([MPTBlock(device=config.init_device, **config.to_dict()) for _ in range(config.n_layers)])
         self.norm_f = norm_class(config.d_model, device=config.init_device)
         if config.init_device != 'meta':
-            print(f'You are using config.init_device={config.init_device!r}, but you can also use config.init_device="meta" with Composer + FSDP for fast initialization.')
+            log.info(f'We recommend using config.init_device="meta" with Composer + FSDP for faster initialization.')
             self.apply(self.param_init_fn)
         self.is_causal = not self.prefix_lm
         self._attn_bias_initialized = False
@@ -66,25 +72,22 @@ class MPTModel(MPTPreTrainedModel):
         if config.no_bias:
             for module in self.modules():
                 if hasattr(module, 'bias') and isinstance(module.bias, nn.Parameter):
-                    if config.verbose:
-                        warnings.warn(f'Removing bias ({module.bias}) from {module}.')
+                    log.info(f'Removing bias ({module.bias}) from {module}.')
                     module.register_parameter('bias', None)
-        if config.verbose and config.verbose > 2:
-            print(self)
-        if 'verbose' not in self.config.init_config:
-            self.config.init_config['verbose'] = self.config.verbose
-        if self.config.init_config['verbose'] > 1:
-            init_fn_name = self.config.init_config['name']
-            warnings.warn(f'Using {init_fn_name} initialization.')
+                if hasattr(module, 'use_bias'):
+                    log.info(f'Setting use_bias=False for {module}.')
+                    module.use_bias = False
+        log.debug(self)
+        log.debug(f"Using {self.config.init_config['name']} initialization.")
 
-    def get_input_embeddings(self):
+    def get_input_embeddings(self) -> nn.Embedding:
         return self.wte
 
-    def set_input_embeddings(self, value):
+    def set_input_embeddings(self, value: nn.Embedding) -> None:
         self.wte = value
 
     @torch.no_grad()
-    def _attn_bias(self, device, dtype, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None):
+    def _attn_bias(self, device: torch.device, dtype: torch.dtype, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None) -> Tuple[Optional[torch.Tensor], Optional[torch.ByteTensor]]:
         if not self._attn_bias_initialized:
             if self.attn_bias_shape:
                 self.attn_bias = torch.zeros(self.attn_bias_shape, device=device, dtype=dtype)
@@ -115,7 +118,7 @@ class MPTModel(MPTPreTrainedModel):
             attn_bias = attn_bias.masked_fill(~attention_mask.view(-1, 1, 1, s_k), min_val)
         return (attn_bias, None)
 
-    def _apply_prefix_mask(self, attn_bias: torch.Tensor, prefix_mask: torch.Tensor):
+    def _apply_prefix_mask(self, attn_bias: torch.Tensor, prefix_mask: torch.Tensor) -> torch.Tensor:
         (s_k, s_q) = attn_bias.shape[-2:]
         if s_k != self.config.max_seq_len or s_q != self.config.max_seq_len:
             raise ValueError('attn_bias does not match the expected shape. ' + f'The last two dimensions should both be {self.config.max_length} ' + f'but are {s_k} and {s_q}.')
@@ -130,7 +133,7 @@ class MPTModel(MPTPreTrainedModel):
         attn_bias = attn_bias.masked_fill(cannot_attend, min_val)
         return attn_bias
 
-    def _apply_sequence_id(self, attn_bias: torch.Tensor, sequence_id: torch.LongTensor):
+    def _apply_sequence_id(self, attn_bias: torch.Tensor, sequence_id: torch.LongTensor) -> torch.Tensor:
         seq_len = sequence_id.shape[-1]
         if seq_len > self.config.max_seq_len:
             raise ValueError(f'sequence_id sequence length cannot exceed max_seq_len={self.config.max_seq_len}')
@@ -140,7 +143,7 @@ class MPTModel(MPTPreTrainedModel):
         attn_bias = attn_bias.masked_fill(cannot_attend, min_val)
         return attn_bias
 
-    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None, inputs_embeds: Optional[torch.Tensor]=None):
+    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None, inputs_embeds: Optional[torch.Tensor]=None) -> BaseModelOutputWithPast:
         return_dict = return_dict if return_dict is not None else self.config.return_dict
         use_cache = use_cache if use_cache is not None else self.config.use_cache
         if attention_mask is not None:
@@ -152,7 +155,7 @@ class MPTModel(MPTPreTrainedModel):
         if output_attentions:
             if self.attn_impl != 'torch':
                 raise NotImplementedError('output_attentions is not implemented for MPT when using attn_impl `flash` or `triton`.')
-        if attention_mask is not None and attention_mask[:, 0].sum() != attention_mask.shape[0] and self.training:
+        if self.training and attention_mask is not None and (attention_mask[:, 0].sum() != attention_mask.shape[0]):
             raise NotImplementedError('MPT does not support training with left padding.')
         if self.prefix_lm and prefix_mask is None:
             raise ValueError('prefix_mask is a required argument when MPT is configured with prefix_lm=True.')
@@ -166,9 +169,7 @@ class MPTModel(MPTPreTrainedModel):
         S = input_ids.size(1)
         assert S <= self.config.max_seq_len, f'Cannot forward input with seq_len={S}, this model only supports seq_len<={self.config.max_seq_len}'
         tok_emb = self.wte(input_ids)
-        if self.alibi:
-            x = tok_emb
-        else:
+        if self.learned_pos_emb:
             past_position = 0
             if past_key_values is not None:
                 if len(past_key_values) != self.config.n_layers:
@@ -177,12 +178,14 @@ class MPTModel(MPTPreTrainedModel):
                 if self.attn_impl == 'torch':
                     past_position = past_key_values[0][0].size(3)
             if S + past_position > self.config.max_seq_len:
-                raise ValueError(f'Cannot forward input with past sequence length {past_position} and current sequence length {S + 1}, this model only supports total sequence length <= {self.config.max_seq_len}.')
+                raise ValueError(f'Cannot forward input with past sequence length {past_position} and current sequence length ' + f'{S + 1}, this model only supports total sequence length <= {self.config.max_seq_len}.')
             pos = torch.arange(past_position, S + past_position, dtype=torch.long, device=input_ids.device).unsqueeze(0)
             if attention_mask is not None:
                 pos = torch.clamp(pos - torch.cumsum((~attention_mask).to(torch.int32), dim=1)[:, past_position:], min=0)
             pos_emb = self.wpe(pos)
             x = tok_emb + pos_emb
+        else:
+            x = tok_emb
         if self.embedding_fraction == 1:
             x = self.emb_drop(x)
         else:
@@ -190,6 +193,7 @@ class MPTModel(MPTPreTrainedModel):
             assert isinstance(self.emb_drop, nn.Module)
             x = self.emb_drop(x_shrunk)
         (attn_bias, attention_mask) = self._attn_bias(device=x.device, dtype=torch.float32, attention_mask=attention_mask, prefix_mask=prefix_mask, sequence_id=sequence_id)
+        presents = () if use_cache else None
         if use_cache and past_key_values is None:
             past_key_values = [() for _ in range(self.config.n_layers)]
         all_hidden_states = () if output_hidden_states else None
@@ -199,9 +203,9 @@ class MPTModel(MPTPreTrainedModel):
                 assert all_hidden_states is not None
                 all_hidden_states = all_hidden_states + (x,)
             past_key_value = past_key_values[b_idx] if past_key_values is not None else None
-            (x, attn_weights, past_key_value) = block(x, past_key_value=past_key_value, attn_bias=attn_bias, attention_mask=attention_mask, is_causal=self.is_causal)
-            if past_key_values is not None:
-                past_key_values[b_idx] = past_key_value
+            (x, attn_weights, present) = block(x, past_key_value=past_key_value, attn_bias=attn_bias, attention_mask=attention_mask, is_causal=self.is_causal, output_attentions=bool(output_attentions))
+            if presents is not None:
+                presents += (present,)
             if output_attentions:
                 assert all_self_attns is not None
                 all_self_attns = all_self_attns + (attn_weights,)
@@ -209,16 +213,16 @@ class MPTModel(MPTPreTrainedModel):
         if output_hidden_states:
             assert all_hidden_states is not None
             all_hidden_states = all_hidden_states + (x,)
-        return BaseModelOutputWithPast(last_hidden_state=x, past_key_values=past_key_values, hidden_states=all_hidden_states, attentions=all_self_attns)
+        return BaseModelOutputWithPast(last_hidden_state=x, past_key_values=presents, hidden_states=all_hidden_states, attentions=all_self_attns)
 
-    def param_init_fn(self, module):
+    def param_init_fn(self, module: nn.Module) -> None:
         init_fn_name = self.config.init_config['name']
         MODEL_INIT_REGISTRY[init_fn_name](module=module, n_layers=self.config.n_layers, d_model=self.config.d_model, **self.config.init_config)
 
-    def fsdp_wrap_fn(self, module):
+    def fsdp_wrap_fn(self, module: nn.Module) -> bool:
         return isinstance(module, MPTBlock)
 
-    def activation_checkpointing_fn(self, module):
+    def activation_checkpointing_fn(self, module: nn.Module) -> bool:
         return isinstance(module, MPTBlock)
 
 class MPTForCausalLM(MPTPreTrainedModel):
@@ -227,8 +231,8 @@ class MPTForCausalLM(MPTPreTrainedModel):
         super().__init__(config)
         if not config.tie_word_embeddings:
             raise ValueError('MPTForCausalLM only supports tied word embeddings')
-        print(f'Instantiating an MPTForCausalLM model from {__file__}')
-        self.transformer = MPTModel(config)
+        log.info(f'Instantiating an MPTForCausalLM model from {__file__}')
+        self.transformer: MPTModel = MPTModel(config)
         for child in self.transformer.children():
             if isinstance(child, torch.nn.ModuleList):
                 continue
@@ -244,25 +248,25 @@ class MPTForCausalLM(MPTPreTrainedModel):
                     raise ValueError(f"logit_scale={logit_scale!r} is not recognized as an option; use numeric value or 'inv_sqrt_d_model'.")
             self.logit_scale = logit_scale
 
-    def get_input_embeddings(self):
+    def get_input_embeddings(self) -> nn.Embedding:
         return self.transformer.wte
 
-    def set_input_embeddings(self, value):
+    def set_input_embeddings(self, value: Union[SharedEmbedding, nn.Embedding]) -> None:
         self.transformer.wte = value
 
-    def get_output_embeddings(self):
+    def get_output_embeddings(self) -> nn.Embedding:
         return self.transformer.wte
 
-    def set_output_embeddings(self, new_embeddings):
+    def set_output_embeddings(self, new_embeddings: Union[SharedEmbedding, nn.Embedding]) -> None:
         self.transformer.wte = new_embeddings
 
-    def set_decoder(self, decoder):
+    def set_decoder(self, decoder: MPTModel) -> None:
         self.transformer = decoder
 
-    def get_decoder(self):
+    def get_decoder(self) -> MPTModel:
         return self.transformer
 
-    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, labels: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None, inputs_embeds: Optional[torch.FloatTensor]=None):
+    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, labels: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None, inputs_embeds: Optional[torch.FloatTensor]=None) -> CausalLMOutputWithPast:
         return_dict = return_dict if return_dict is not None else self.config.return_dict
         use_cache = use_cache if use_cache is not None else self.config.use_cache
         if inputs_embeds is not None:
@@ -275,22 +279,22 @@ class MPTForCausalLM(MPTPreTrainedModel):
             logits *= self.logit_scale
         loss = None
         if labels is not None:
-            labels = torch.roll(labels, shifts=-1)
-            labels[:, -1] = -100
-            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), labels.to(logits.device).view(-1))
+            _labels = torch.roll(labels, shifts=-1)
+            _labels[:, -1] = -100
+            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), _labels.to(logits.device).view(-1))
         return CausalLMOutputWithPast(loss=loss, logits=logits, past_key_values=outputs.past_key_values, hidden_states=outputs.hidden_states, attentions=outputs.attentions)
 
-    def param_init_fn(self, module):
+    def param_init_fn(self, module: nn.Module) -> None:
         init_fn_name = self.config.init_config['name']
         MODEL_INIT_REGISTRY[init_fn_name](module=module, n_layers=self.config.n_layers, d_model=self.config.d_model, **self.config.init_config)
 
-    def fsdp_wrap_fn(self, module):
+    def fsdp_wrap_fn(self, module: nn.Module) -> bool:
         return isinstance(module, MPTBlock)
 
-    def activation_checkpointing_fn(self, module):
+    def activation_checkpointing_fn(self, module: nn.Module) -> bool:
         return isinstance(module, MPTBlock)
 
-    def prepare_inputs_for_generation(self, input_ids, past_key_values=None, inputs_embeds=None, **kwargs):
+    def prepare_inputs_for_generation(self, input_ids: torch.Tensor, past_key_values: Optional[List[Tuple[torch.Tensor, torch.Tensor]]]=None, inputs_embeds: Optional[torch.Tensor]=None, **kwargs: Any) -> Dict[str, Any]:
         if inputs_embeds is not None:
             raise NotImplementedError('inputs_embeds is not implemented for MPT yet')
         attention_mask = kwargs['attention_mask'].bool()
@@ -311,7 +315,7 @@ class MPTForCausalLM(MPTPreTrainedModel):
         return {'input_ids': input_ids, 'attention_mask': attention_mask, 'prefix_mask': prefix_mask, 'sequence_id': sequence_id, 'past_key_values': past_key_values, 'use_cache': kwargs.get('use_cache', True)}
 
     @staticmethod
-    def _reorder_cache(past_key_values, beam_idx):
+    def _reorder_cache(past_key_values: List[Tuple[torch.Tensor, torch.Tensor]], beam_idx: torch.LongTensor) -> List[Tuple[torch.Tensor, ...]]:
         """Used by HuggingFace generate when using beam search with kv-caching.
 
         See https://github.com/huggingface/transformers/blob/3ec7a47664ebe40c40f4b722f6bb1cd30c3821ec/src/transformers/models/gpt2/modeling_gpt2.py#L1122-L1133

norm.py

@@ -1,6 +1,7 @@
+from typing import Dict, List, Optional, Type, Union
 import torch
 
-def _cast_if_autocast_enabled(tensor):
+def _cast_if_autocast_enabled(tensor: torch.Tensor) -> torch.Tensor:
     if torch.is_autocast_enabled():
         if tensor.device.type == 'cuda':
             dtype = torch.get_autocast_gpu_dtype()
@@ -13,10 +14,10 @@ def _cast_if_autocast_enabled(tensor):
 
 class LPLayerNorm(torch.nn.LayerNorm):
 
-    def __init__(self, normalized_shape, eps=1e-05, elementwise_affine=True, device=None, dtype=None):
+    def __init__(self, normalized_shape: Union[int, List[int], torch.Size], eps: float=1e-05, elementwise_affine: bool=True, device: Optional[torch.device]=None, dtype: Optional[torch.dtype]=None):
         super().__init__(normalized_shape=normalized_shape, eps=eps, elementwise_affine=elementwise_affine, device=device, dtype=dtype)
 
-    def forward(self, x):
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
         module_device = x.device
         downcast_x = _cast_if_autocast_enabled(x)
         downcast_weight = _cast_if_autocast_enabled(self.weight) if self.weight is not None else self.weight
@@ -24,7 +25,7 @@ class LPLayerNorm(torch.nn.LayerNorm):
         with torch.autocast(enabled=False, device_type=module_device.type):
             return torch.nn.functional.layer_norm(downcast_x, self.normalized_shape, downcast_weight, downcast_bias, self.eps)
 
-def rms_norm(x, weight=None, eps=1e-05):
+def rms_norm(x: torch.Tensor, weight: Optional[torch.Tensor]=None, eps: float=1e-05) -> torch.Tensor:
     output = x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + eps)
     if weight is not None:
         return output * weight
@@ -32,7 +33,7 @@ def rms_norm(x, weight=None, eps=1e-05):
 
 class RMSNorm(torch.nn.Module):
 
-    def __init__(self, normalized_shape, eps=1e-05, weight=True, dtype=None, device=None):
+    def __init__(self, normalized_shape: Union[int, List[int], torch.Size], eps: float=1e-05, weight: bool=True, dtype: Optional[torch.dtype]=None, device: Optional[torch.device]=None):
         super().__init__()
         self.eps = eps
         if weight:
@@ -40,17 +41,17 @@ class RMSNorm(torch.nn.Module):
         else:
             self.register_parameter('weight', None)
 
-    def forward(self, x):
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
         return rms_norm(x.float(), self.weight, self.eps).to(dtype=x.dtype)
 
 class LPRMSNorm(RMSNorm):
 
-    def __init__(self, normalized_shape, eps=1e-05, weight=True, dtype=None, device=None):
+    def __init__(self, normalized_shape: Union[int, List[int], torch.Size], eps: float=1e-05, weight: bool=True, dtype: Optional[torch.dtype]=None, device: Optional[torch.device]=None):
         super().__init__(normalized_shape=normalized_shape, eps=eps, weight=weight, dtype=dtype, device=device)
 
-    def forward(self, x):
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
         downcast_x = _cast_if_autocast_enabled(x)
         downcast_weight = _cast_if_autocast_enabled(self.weight) if self.weight is not None else self.weight
         with torch.autocast(enabled=False, device_type=x.device.type):
             return rms_norm(downcast_x, downcast_weight, self.eps).to(dtype=x.dtype)
-NORM_CLASS_REGISTRY = {'layernorm': torch.nn.LayerNorm, 'low_precision_layernorm': LPLayerNorm, 'rmsnorm': RMSNorm, 'low_precision_rmsnorm': LPRMSNorm}
+NORM_CLASS_REGISTRY: Dict[str, Type[torch.nn.Module]] = {'layernorm': torch.nn.LayerNorm, 'low_precision_layernorm': LPLayerNorm, 'rmsnorm': RMSNorm, 'low_precision_rmsnorm': LPRMSNorm}

param_init_fns.py

@@ -2,22 +2,26 @@ import math
 import warnings
 from collections.abc import Sequence
 from functools import partial
-from typing import Optional, Tuple, Union
+from typing import Any, Callable, Optional, Tuple, Union
 import torch
 from torch import nn
+from .fc import FC_CLASS_REGISTRY
 from .norm import NORM_CLASS_REGISTRY
+try:
+    import transformer_engine.pytorch as te
+except:
+    te = None
 
-def torch_default_param_init_fn_(module: nn.Module, verbose: int=0, **kwargs):
+def torch_default_param_init_fn_(module: nn.Module, **kwargs: Any) -> None:
     del kwargs
-    if verbose > 1:
-        warnings.warn(f"Initializing network using module's reset_parameters attribute")
-    if hasattr(module, 'reset_parameters'):
+    if hasattr(module, 'reset_parameters') and isinstance(module.reset_parameters, Callable):
         module.reset_parameters()
 
-def fused_init_helper_(module: nn.Module, init_fn_):
+def fused_init_helper_(module: nn.Module, init_fn_: Callable) -> None:
     _fused = getattr(module, '_fused', None)
     if _fused is None:
         raise RuntimeError(f'Internal logic error')
+    assert isinstance(module.weight, torch.Tensor)
     (dim, splits) = _fused
     splits = (0, *splits, module.weight.size(dim))
     for (s, e) in zip(splits[:-1], splits[1:]):
@@ -25,10 +29,8 @@ def fused_init_helper_(module: nn.Module, init_fn_):
         slice_indices[dim] = slice(s, e)
         init_fn_(module.weight[slice_indices])
 
-def generic_param_init_fn_(module: nn.Module, init_fn_, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, verbose: int=0, **kwargs):
+def generic_param_init_fn_(module: nn.Module, init_fn_: Callable, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, **kwargs: Any) -> None:
     del kwargs
-    if verbose > 1:
-        warnings.warn(f'If model has bias parameters they are initialized to 0.')
     init_div_is_residual = init_div_is_residual
     if init_div_is_residual is False:
         div_is_residual = 1.0
@@ -36,20 +38,18 @@ def generic_param_init_fn_(module: nn.Module, init_fn_, n_layers: int, d_model:
         div_is_residual = math.sqrt(2 * n_layers)
     elif isinstance(init_div_is_residual, float) or isinstance(init_div_is_residual, int):
         div_is_residual = init_div_is_residual
-    elif isinstance(init_div_is_residual, str) and init_div_is_residual.isnumeric():
+    elif init_div_is_residual.isnumeric():
         div_is_residual = float(init_div_is_residual)
     else:
         div_is_residual = 1.0
         raise ValueError(f'Expected init_div_is_residual to be boolean or numeric, got {init_div_is_residual}')
-    if init_div_is_residual is not False:
-        if verbose > 1:
-            warnings.warn(f'Initializing _is_residual layers then dividing them by {div_is_residual:.3f}. ' + f'Set `init_div_is_residual: false` in init config to disable this.')
-    if isinstance(module, nn.Linear):
+    if isinstance(module, tuple(set(FC_CLASS_REGISTRY.values()))):
         if hasattr(module, '_fused'):
             fused_init_helper_(module, init_fn_)
         else:
             init_fn_(module.weight)
         if module.bias is not None:
+            assert isinstance(module.bias, torch.Tensor)
             torch.nn.init.zeros_(module.bias)
         if init_div_is_residual is not False and getattr(module, '_is_residual', False):
             with torch.no_grad():
@@ -60,8 +60,6 @@ def generic_param_init_fn_(module: nn.Module, init_fn_, n_layers: int, d_model:
             if std == 0:
                 warnings.warn(f'Embedding layer initialized to 0.')
             emb_init_fn_ = partial(torch.nn.init.normal_, mean=0.0, std=std)
-            if verbose > 1:
-                warnings.warn(f'Embedding layer initialized using normal distribution with mean=0 and std={std!r}.')
         elif emb_init_uniform_lim is not None:
             lim = emb_init_uniform_lim
             if isinstance(lim, Sequence):
@@ -75,17 +73,13 @@ def generic_param_init_fn_(module: nn.Module, init_fn_, n_layers: int, d_model:
                 lim = [-lim, lim]
             (a, b) = lim
             emb_init_fn_ = partial(torch.nn.init.uniform_, a=a, b=b)
-            if verbose > 1:
-                warnings.warn(f'Embedding layer initialized using uniform distribution in range {lim}.')
         else:
             emb_init_fn_ = init_fn_
         emb_init_fn_(module.weight)
     elif isinstance(module, tuple(set(NORM_CLASS_REGISTRY.values()))):
-        if verbose > 1:
-            warnings.warn(f'Norm weights are set to 1. If norm layer has a bias it is initialized to 0.')
-        if hasattr(module, 'weight') and module.weight is not None:
+        if hasattr(module, 'weight') and isinstance(module.weight, torch.Tensor):
             torch.nn.init.ones_(module.weight)
-        if hasattr(module, 'bias') and module.bias is not None:
+        if hasattr(module, 'bias') and isinstance(module.bias, torch.Tensor):
             torch.nn.init.zeros_(module.bias)
     elif isinstance(module, nn.MultiheadAttention):
         if module._qkv_same_embed_dim:
@@ -114,32 +108,45 @@ def generic_param_init_fn_(module: nn.Module, init_fn_, n_layers: int, d_model:
                 module.out_proj.weight.div_(div_is_residual)
         if module.out_proj.bias is not None:
             torch.nn.init.zeros_(module.out_proj.bias)
+    elif te is not None and isinstance(module, te.LayerNormMLP):
+        if isinstance(module.layer_norm_weight, torch.Tensor):
+            torch.nn.init.ones_(module.layer_norm_weight)
+        if isinstance(module.layer_norm_bias, torch.Tensor):
+            torch.nn.init.zeros_(module.layer_norm_bias)
+        init_fn_(module.fc1_weight)
+        if module.fc1_bias is not None:
+            assert isinstance(module.fc1_bias, torch.Tensor)
+            torch.nn.init.zeros_(module.fc1_bias)
+        init_fn_(module.fc2_weight)
+        if module.fc2_bias is not None:
+            assert isinstance(module.fc2_bias, torch.Tensor)
+            torch.nn.init.zeros_(module.fc2_bias)
+        with torch.no_grad():
+            module.fc2_weight.div_(div_is_residual)
     else:
         for _ in module.parameters(recurse=False):
             raise NotImplementedError(f'{module.__class__.__name__} parameters are not initialized by param_init_fn.')
 
-def _normal_init_(std, mean=0.0):
+def _normal_init_(std: float, mean: float=0.0) -> Callable:
     return partial(torch.nn.init.normal_, mean=mean, std=std)
 
-def _normal_param_init_fn_(module: nn.Module, std: float, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, verbose: int=0, **kwargs):
+def _normal_param_init_fn_(module: nn.Module, std: float, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, **kwargs: Any) -> None:
     del kwargs
     init_fn_ = _normal_init_(std=std)
-    if verbose > 1:
-        warnings.warn(f'Using torch.nn.init.normal_ init fn mean=0.0, std={std}')
-    generic_param_init_fn_(module=module, init_fn_=init_fn_, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim, verbose=verbose)
+    generic_param_init_fn_(module=module, init_fn_=init_fn_, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim)
 
-def baseline_param_init_fn_(module: nn.Module, init_std: float, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, verbose: int=0, **kwargs):
+def baseline_param_init_fn_(module: nn.Module, init_std: Optional[float], n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, **kwargs: Any) -> None:
     del kwargs
     if init_std is None:
         raise ValueError("You must set model.init_config['init_std'] to a float value to use the default initialization scheme.")
-    _normal_param_init_fn_(module=module, std=init_std, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim, verbose=verbose)
+    _normal_param_init_fn_(module=module, std=init_std, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim)
 
-def small_param_init_fn_(module: nn.Module, n_layers: int, d_model: int, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, verbose: int=0, **kwargs):
+def small_param_init_fn_(module: nn.Module, n_layers: int, d_model: int, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, **kwargs: Any) -> None:
     del kwargs
     std = math.sqrt(2 / (5 * d_model))
-    _normal_param_init_fn_(module=module, std=std, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim, verbose=verbose)
+    _normal_param_init_fn_(module=module, std=std, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim)
 
-def neox_param_init_fn_(module: nn.Module, n_layers: int, d_model: int, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, verbose: int=0, **kwargs):
+def neox_param_init_fn_(module: nn.Module, n_layers: int, d_model: int, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, **kwargs: Any) -> None:
     """From section 2.3.1 of GPT-NeoX-20B:
 
     An Open-Source AutoregressiveLanguage Model — Black et. al. (2022)
@@ -148,34 +155,25 @@ def neox_param_init_fn_(module: nn.Module, n_layers: int, d_model: int, emb_init
     """
     del kwargs
     residual_div = n_layers / math.sqrt(10)
-    if verbose > 1:
-        warnings.warn(f'setting init_div_is_residual to {residual_div}')
-    small_param_init_fn_(module=module, d_model=d_model, n_layers=n_layers, init_div_is_residual=residual_div, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim, verbose=verbose)
+    small_param_init_fn_(module=module, d_model=d_model, n_layers=n_layers, init_div_is_residual=residual_div, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim)
 
-def kaiming_uniform_param_init_fn_(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, init_gain: float=0, fan_mode: str='fan_in', init_nonlinearity: str='leaky_relu', verbose: int=0, **kwargs):
+def kaiming_uniform_param_init_fn_(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, init_gain: float=0, fan_mode: str='fan_in', init_nonlinearity: str='leaky_relu', **kwargs: Any) -> None:
     del kwargs
-    if verbose > 1:
-        warnings.warn(f'Using nn.init.kaiming_uniform_ init fn with parameters: ' + f'a={init_gain}, mode={fan_mode}, nonlinearity={init_nonlinearity}')
     kaiming_uniform_ = partial(nn.init.kaiming_uniform_, a=init_gain, mode=fan_mode, nonlinearity=init_nonlinearity)
-    generic_param_init_fn_(module=module, init_fn_=kaiming_uniform_, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim, verbose=verbose)
+    generic_param_init_fn_(module=module, init_fn_=kaiming_uniform_, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim)
 
-def kaiming_normal_param_init_fn_(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, init_gain: float=0, fan_mode: str='fan_in', init_nonlinearity: str='leaky_relu', verbose: int=0, **kwargs):
+def kaiming_normal_param_init_fn_(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, init_gain: float=0, fan_mode: str='fan_in', init_nonlinearity: str='leaky_relu', **kwargs: Any) -> None:
     del kwargs
-    if verbose > 1:
-        warnings.warn(f'Using nn.init.kaiming_normal_ init fn with parameters: ' + f'a={init_gain}, mode={fan_mode}, nonlinearity={init_nonlinearity}')
     kaiming_normal_ = partial(torch.nn.init.kaiming_normal_, a=init_gain, mode=fan_mode, nonlinearity=init_nonlinearity)
-    generic_param_init_fn_(module=module, init_fn_=kaiming_normal_, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim, verbose=verbose)
+    generic_param_init_fn_(module=module, init_fn_=kaiming_normal_, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim)
 
-def xavier_uniform_param_init_fn_(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, init_gain: float=0, verbose: int=0, **kwargs):
+def xavier_uniform_param_init_fn_(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, init_gain: float=0, **kwargs: Any) -> None:
     del kwargs
     xavier_uniform_ = partial(torch.nn.init.xavier_uniform_, gain=init_gain)
-    if verbose > 1:
-        warnings.warn(f'Using torch.nn.init.xavier_uniform_ init fn with parameters: ' + f'gain={init_gain}')
-    generic_param_init_fn_(module=module, init_fn_=xavier_uniform_, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim, verbose=verbose)
+    generic_param_init_fn_(module=module, init_fn_=xavier_uniform_, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim)
 
-def xavier_normal_param_init_fn_(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, init_gain: float=0, verbose: int=0, **kwargs):
+def xavier_normal_param_init_fn_(module: nn.Module, n_layers: int, d_model: Optional[int]=None, init_div_is_residual: Union[int, float, str, bool]=True, emb_init_std: Optional[float]=None, emb_init_uniform_lim: Optional[Union[Tuple[float, float], float]]=None, init_gain: float=0, **kwargs: Any) -> None:
+    del kwargs
     xavier_normal_ = partial(torch.nn.init.xavier_normal_, gain=init_gain)
-    if verbose > 1:
-        warnings.warn(f'Using torch.nn.init.xavier_normal_ init fn with parameters: ' + f'gain={init_gain}')
-    generic_param_init_fn_(module=module, init_fn_=xavier_normal_, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim, verbose=verbose)
+    generic_param_init_fn_(module=module, init_fn_=xavier_normal_, d_model=d_model, n_layers=n_layers, init_div_is_residual=init_div_is_residual, emb_init_std=emb_init_std, emb_init_uniform_lim=emb_init_uniform_lim)
 MODEL_INIT_REGISTRY = {'default_': torch_default_param_init_fn_, 'baseline_': baseline_param_init_fn_, 'kaiming_uniform_': kaiming_uniform_param_init_fn_, 'kaiming_normal_': kaiming_normal_param_init_fn_, 'neox_init_': neox_param_init_fn_, 'small_init_': small_param_init_fn_, 'xavier_uniform_': xavier_uniform_param_init_fn_, 'xavier_normal_': xavier_normal_param_init_fn_}