Convert ReplitLM to MPT (#16)

- Convert ReplitLM to MPT (2635241d5b35bf63b8652513c212f645b78b1572)


Co-authored-by: Madhav <madhavatreplit@users.noreply.huggingface.co>

README.md

@@ -173,9 +173,4 @@ Note that as with all code generation models, post-processing of the generated c
 - stop generation when the EOS token is encountered
 - remove trailing whitespaces
 - set `max_tokens` to a reasonable value based on your completion use case
-- truncate generation to stop words such as `return`, `def`, "```", "`\n\n\n`" to avoid generating incomplete code when `max_tokens` is larger than the length of the expected generated code.
-
-
-
-## Model Hash
-5bc28ce32c6f9aec935ead7b60ea1c46
+- truncate generation to stop words such as `return`, `def`, "```", "`\n\n\n`" to avoid generating incomplete code when `max_tokens` is larger than the length of the expected generated code.

adapt_tokenizer.py

@@ -0,0 +1,41 @@
+from typing import Union
+from transformers import AutoTokenizer, PreTrainedTokenizer, PreTrainedTokenizerFast
+Tokenizer = Union[PreTrainedTokenizer, PreTrainedTokenizerFast]
+NUM_SENTINEL_TOKENS: int = 100
+
+def adapt_tokenizer_for_denoising(tokenizer: Tokenizer):
+    """Adds sentinel tokens and padding token (if missing).
+
+    Expands the tokenizer vocabulary to include sentinel tokens
+    used in mixture-of-denoiser tasks as well as a padding token.
+
+    All added tokens are added as special tokens. No tokens are
+    added if sentinel tokens and padding token already exist.
+    """
+    sentinels_to_add = [f'<extra_id_{i}>' for i in range(NUM_SENTINEL_TOKENS)]
+    tokenizer.add_tokens(sentinels_to_add, special_tokens=True)
+    if tokenizer.pad_token is None:
+        tokenizer.add_tokens('<pad>', special_tokens=True)
+        tokenizer.pad_token = '<pad>'
+        assert tokenizer.pad_token_id is not None
+    sentinels = ''.join([f'<extra_id_{i}>' for i in range(NUM_SENTINEL_TOKENS)])
+    _sentinel_token_ids = tokenizer(sentinels, add_special_tokens=False).input_ids
+    tokenizer.sentinel_token_ids = _sentinel_token_ids
+
+class AutoTokenizerForMOD(AutoTokenizer):
+    """AutoTokenizer + Adaptation for MOD.
+
+    A simple wrapper around AutoTokenizer to make instantiating
+    an MOD-adapted tokenizer a bit easier.
+
+    MOD-adapted tokenizers have sentinel tokens (e.g., <extra_id_0>),
+    a padding token, and a property to get the token ids of the
+    sentinel tokens.
+    """
+
+    @classmethod
+    def from_pretrained(cls, *args, **kwargs):
+        """See `AutoTokenizer.from_pretrained` docstring."""
+        tokenizer = super().from_pretrained(*args, **kwargs)
+        adapt_tokenizer_for_denoising(tokenizer)
+        return tokenizer

attention.py

@@ -1,80 +1,39 @@
-# Copyright 2022 MosaicML Examples authors
-# SPDX-License-Identifier: Apache-2.0
-
 """Attention layers."""
-
 import math
 import warnings
 from typing import Optional
-
 import torch
+import torch.nn as nn
 from einops import rearrange
 from torch import nn
+from .norm import LPLayerNorm
 
-from .low_precision_layernorm import LPLayerNorm
-
-
-def _reset_is_causal(num_query_tokens: int, num_key_tokens: int,
-                     original_is_causal: bool):
+def _reset_is_causal(num_query_tokens: int, num_key_tokens: int, original_is_causal: bool):
     if original_is_causal and num_query_tokens != num_key_tokens:
         if num_query_tokens != 1:
-            raise NotImplementedError(
-                'ReplitLM does not support query and key with different number of tokens, unless number of query tokens is 1.'
-            )
+            raise NotImplementedError('MPT does not support query and key with different number of tokens, unless number of query tokens is 1.')
         else:
             return False
     return original_is_causal
 
-
-def scaled_multihead_dot_product_attention(
-    query,
-    key,
-    value,
-    n_heads,
-    softmax_scale=None,
-    attn_bias=None,
-    key_padding_mask=None,
-    is_causal=False,
-    dropout_p=0.0,
-    training=False,
-    needs_weights=False,
-):
-
+def scaled_multihead_dot_product_attention(query, key, value, n_heads, softmax_scale=None, attn_bias=None, key_padding_mask=None, is_causal=False, dropout_p=0.0, training=False, needs_weights=False, multiquery=False):
     q = rearrange(query, 'b s (h d) -> b h s d', h=n_heads)
-    k = rearrange(key, 'b s (h d) -> b h d s', h=n_heads)  # includes key.t()
-    v = rearrange(value, 'b s (h d) -> b h s d', h=n_heads)
-
+    k = rearrange(key, 'b s (h d) -> b h d s', h=1 if multiquery else n_heads)
+    v = rearrange(value, 'b s (h d) -> b h s d', h=1 if multiquery else n_heads)
     min_val = torch.finfo(q.dtype).min
-
-    b, _, s_q, d = q.shape
+    (b, _, s_q, d) = q.shape
     s_k = k.size(-1)
-
     if softmax_scale is None:
         softmax_scale = 1 / math.sqrt(d)
-
     attn_weight = q.matmul(k) * softmax_scale
-
     if attn_bias is not None:
-        if (attn_bias.size(-1) != 1 and
-                attn_bias.size(-1) != s_k) or (attn_bias.size(-2) != 1 and
-                                               attn_bias.size(-2) != s_q):
-            raise RuntimeError(
-                f'attn_bias (shape: {attn_bias.shape}) is expected to broadcast to shape: {attn_weight.shape}.'
-            )
+        if attn_bias.size(-1) != 1 and attn_bias.size(-1) != s_k or (attn_bias.size(-2) != 1 and attn_bias.size(-2) != s_q):
+            raise RuntimeError(f'attn_bias (shape: {attn_bias.shape}) is expected to broadcast to shape: {attn_weight.shape}.')
         attn_weight = attn_weight + attn_bias
-
     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.'
-            )
-        attn_weight = attn_weight.masked_fill(
-            ~key_padding_mask.view((b, 1, 1, s_k)), min_val)
-
+            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.')
+        attn_weight = attn_weight.masked_fill(~key_padding_mask.view((b, 1, 1, s_k)), min_val)
     if is_causal:
         s = max(s_q, s_k)
         causal_mask = attn_weight.new_ones(s, s, dtype=torch.float16)
@@ -82,156 +41,76 @@ def scaled_multihead_dot_product_attention(
         causal_mask = causal_mask.to(torch.bool)
         causal_mask = ~causal_mask
         causal_mask = causal_mask[-s_q:, -s_k:]
-        attn_weight = attn_weight.masked_fill(causal_mask.view(1, 1, s_q, s_k),
-                                              min_val)
-
+        attn_weight = attn_weight.masked_fill(causal_mask.view(1, 1, s_q, s_k), min_val)
     attn_weight = torch.softmax(attn_weight, dim=-1)
-
     if dropout_p:
-        attn_weight = torch.nn.functional.dropout(attn_weight,
-                                                  p=dropout_p,
-                                                  training=training,
-                                                  inplace=True)
-
+        attn_weight = torch.nn.functional.dropout(attn_weight, p=dropout_p, training=training, inplace=True)
     out = attn_weight.matmul(v)
     out = rearrange(out, 'b h s d -> b s (h d)')
-
     if needs_weights:
-        return out, attn_weight
-    return out, None
-
+        return (out, attn_weight)
+    return (out, None)
 
 def check_valid_inputs(*tensors, valid_dtypes=[torch.float16, torch.bfloat16]):
     for tensor in tensors:
         if tensor.dtype not in valid_dtypes:
-            raise TypeError(f'{tensor.dtype=} must be 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=}).')
-
+            raise TypeError(f'Inputs must be cuda tensors (tensor.is_cuda={tensor.is_cuda!r}).')
 
-def flash_attn_fn(
-    query,
-    key,
-    value,
-    n_heads,
-    softmax_scale=None,
-    attn_bias=None,
-    key_padding_mask=None,
-    is_causal=False,
-    dropout_p=0.0,
-    training=False,
-    needs_weights=False,
-):
+def flash_attn_fn(query, key, value, n_heads, softmax_scale=None, attn_bias=None, key_padding_mask=None, is_causal=False, dropout_p=0.0, training=False, needs_weights=False, multiquery=False):
     try:
         from flash_attn import bert_padding, flash_attn_interface
     except:
-        raise RuntimeError('Please install flash_attn==0.2.8')
-
+        raise RuntimeError('Please install flash-attn==1.0.3.post0')
     check_valid_inputs(query, key, value)
-
     if attn_bias is not None:
         raise NotImplementedError(f'attn_bias not implemented for flash attn.')
-
-    batch_size, seqlen = query.shape[:2]
-
+    (batch_size, seqlen) = query.shape[:2]
     if key_padding_mask is None:
         key_padding_mask = torch.ones_like(key[:, :, 0], dtype=torch.bool)
     query_padding_mask = key_padding_mask[:, -query.size(1):]
-
-    query_unpad, indices_q, cu_seqlens_q, max_seqlen_q = bert_padding.unpad_input(
-        query, query_padding_mask)
+    (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=n_heads)
-
-    value_unpad, _, _, _ = bert_padding.unpad_input(value, key_padding_mask)
-    value_unpad = rearrange(value_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)
+    (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:
+        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))
     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)
+    output = bert_padding.pad_input(rearrange(output_unpad, 'nnz h d -> nnz (h d)'), indices_q, batch_size, seqlen)
+    return (output, None)
 
-    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)
-
-    output = bert_padding.pad_input(
-        rearrange(output_unpad, 'nnz h d -> nnz (h d)'), indices_q, batch_size,
-        seqlen)
-    return output, None
-
-
-def triton_flash_attn_fn(
-    query,
-    key,
-    value,
-    n_heads,
-    softmax_scale=None,
-    attn_bias=None,
-    key_padding_mask=None,
-    is_causal=False,
-    dropout_p=0.0,
-    training=False,
-    needs_weights=False,
-):
+def triton_flash_attn_fn(query, key, value, n_heads, softmax_scale=None, attn_bias=None, key_padding_mask=None, is_causal=False, dropout_p=0.0, training=False, needs_weights=False, multiquery=False):
     try:
-        from flash_attn import flash_attn_triton  # type: ignore
+        from flash_attn import flash_attn_triton
     except:
-        raise RuntimeError(
-            'Please install flash_attn==0.2.8 and triton==2.0.0.dev20221202.')
-
+        raise RuntimeError('Please install flash-attn==1.0.3.post0 and triton==2.0.0.dev20221202')
     check_valid_inputs(query, key, value)
-
     if dropout_p:
-        raise NotImplementedError(
-            f'Dropout not implemented for attn_impl: triton.')
-
+        raise NotImplementedError(f'Dropout not implemented for attn_impl: triton.')
     if needs_weights:
-        raise NotImplementedError(
-            f'attn_impl: triton cannot return attn weights.')
-
+        raise NotImplementedError(f'attn_impl: triton cannot return attn weights.')
     if key_padding_mask is not None:
-        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.'
-        )
-        b_size, s_k = key_padding_mask.shape[:2]
-
+        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.')
+        (b_size, s_k) = key_padding_mask.shape[:2]
         if attn_bias is None:
             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)
-
+        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=n_heads)
-    value = rearrange(value, '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))
     reset_is_causal = _reset_is_causal(query.size(1), key.size(1), is_causal)
-    attn_output = flash_attn_triton.flash_attn_func(query, key, value,
-                                                    attn_bias, reset_is_causal,
-                                                    softmax_scale)
-
+    attn_output = flash_attn_triton.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
-
+    return (output, None)
 
 class MultiheadAttention(nn.Module):
     """Multi-head self attention.
@@ -240,115 +119,121 @@ class MultiheadAttention(nn.Module):
     additive bias.
     """
 
-    def __init__(
-        self,
-        d_model: int,
-        n_heads: int,
-        attn_impl: str = 'triton',
-        attn_clip_qkv: Optional[float] = None,
-        attn_qk_ln: bool = False,
-        softmax_scale: Optional[float] = None,
-        attn_pdrop: float = 0.0,
-        low_precision_layernorm: bool = False,
-        device: Optional[str] = None,
-    ):
+    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 = attn_clip_qkv
-        self.attn_qk_ln = attn_qk_ln
-
+        self.clip_qkv = clip_qkv
+        self.qk_ln = qk_ln
         self.d_model = d_model
         self.n_heads = 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)
-        # for param init fn; enables shape based init of fused layers
         fuse_splits = (d_model, 2 * d_model)
-        self.Wqkv._fused = (0, fuse_splits)  # type: ignore
-
-        if self.attn_qk_ln:
+        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)
-
         if self.attn_impl == 'flash':
             self.attn_fn = flash_attn_fn
         elif self.attn_impl == 'triton':
             self.attn_fn = triton_flash_attn_fn
-            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`.')
+            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():
-                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`.'
-                )
+            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=} is an invalid setting.')
-
+            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  # type: ignore
+        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, 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.chunk(3, dim=2)
-
+        (query, key, value) = qkv.chunk(3, dim=2)
         key_padding_mask = attention_mask
-
-        if self.attn_qk_ln:
-            # Applying layernorm to qk
+        if self.qk_ln:
             dtype = query.dtype
             query = self.q_ln(query).to(dtype)
             key = self.k_ln(key).to(dtype)
-
         if past_key_value is not None:
             if len(past_key_value) != 0:
                 key = torch.cat([past_key_value[0], key], dim=1)
                 value = torch.cat([past_key_value[1], value], dim=1)
-
             past_key_value = (key, value)
-
         if attn_bias is not None:
             attn_bias = attn_bias[:, :, -query.size(1):, -key.size(1):]
+        (context, attn_weights) = self.attn_fn(query, key, value, self.n_heads, 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)
 
-        context, attn_weights = self.attn_fn(
-            query,
-            key,
-            value,
-            self.n_heads,
-            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,
-        )
+class MultiQueryAttention(nn.Module):
+    """Multi-Query self attention.
 
-        return self.out_proj(context), attn_weights, past_key_value
+    Using torch or triton attention implemetation 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 attn_bias_shape(attn_impl, n_heads, seq_len, alibi, prefix_lm, causal,
-                    use_sequence_id):
+    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)
+        if past_key_value is not None:
+            if len(past_key_value) != 0:
+                key = torch.cat([past_key_value[0], key], dim=1)
+                value = torch.cat([past_key_value[1], value], dim=1)
+            past_key_value = (key, value)
+        if attn_bias is not None:
+            attn_bias = attn_bias[:, :, -query.size(1):, -key.size(1):]
+        (context, attn_weights) = self.attn_fn(query, key, value, self.n_heads, 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)
+
+def attn_bias_shape(attn_impl, n_heads, seq_len, alibi, prefix_lm, causal, use_sequence_id):
     if attn_impl == 'flash':
         return None
     elif attn_impl in ['torch', 'triton']:
@@ -360,50 +245,34 @@ def attn_bias_shape(attn_impl, n_heads, seq_len, alibi, prefix_lm, causal,
             return (1, 1, seq_len, seq_len)
         return None
     else:
-        raise ValueError(f'{attn_impl=} is an invalid setting.')
-
+        raise ValueError(f'attn_impl={attn_impl!r} is an invalid setting.')
 
-def attn_bias(attn_impl,
-              attn_bias,
-              n_heads,
-              seq_len,
-              causal=False,
-              alibi=False,
-              alibi_bias_max=8):
+def build_attn_bias(attn_impl, attn_bias, n_heads, seq_len, causal=False, alibi=False, alibi_bias_max=8):
     if attn_impl == 'flash':
         return None
     elif attn_impl in ['torch', 'triton']:
         if alibi:
-            # in place add alibi to attn bias
-            device, dtype = attn_bias.device, attn_bias.dtype
-            attn_bias = attn_bias.add(
-                alibi_bias(n_heads,
-                           seq_len,
-                           full=not causal,
-                           alibi_bias_max=alibi_bias_max,
-                           device=device,
-                           dtype=dtype))
+            (device, dtype) = (attn_bias.device, attn_bias.dtype)
+            attn_bias = attn_bias.add(build_alibi_bias(n_heads, seq_len, full=not causal, alibi_bias_max=alibi_bias_max, device=device, dtype=dtype))
         return attn_bias
     else:
-        raise ValueError(f'{attn_impl=} is an invalid setting.')
-
-
-def alibi_bias(n_heads,
-               seq_len,
-               full=False,
-               alibi_bias_max=8,
-               device=None,
-               dtype=None):
-    alibi_bias = torch.arange(1 - seq_len, 1, dtype=dtype,
-                              device=device).view(1, 1, 1, seq_len)
+        raise ValueError(f'attn_impl={attn_impl!r} is an invalid setting.')
+
+def gen_slopes(n_heads, alibi_bias_max=8, device=None):
+    _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)
+    slopes = 1.0 / torch.pow(2, m)
+    if _n_heads != n_heads:
+        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):
+    alibi_bias = torch.arange(1 - seq_len, 1, dtype=torch.int32, device=device).view(1, 1, 1, seq_len)
     if full:
-        # generate 1 x Heads x SeqLen x SeqLen alibi bias mask
-        # otherwise the mask is 1 x Heads x 1 x SeqLen (which is broadcast to the appropriate size)
-        alibi_bias = alibi_bias - torch.arange(
-            1 - seq_len, 1, dtype=dtype, device=device).view(1, 1, seq_len, 1)
+        alibi_bias = alibi_bias - torch.arange(1 - seq_len, 1, dtype=torch.int32, device=device).view(1, 1, seq_len, 1)
         alibi_bias = alibi_bias.abs().mul(-1)
-
-    m = torch.arange(1, n_heads + 1, dtype=dtype, device=device)
-    m = m.mul(alibi_bias_max / n_heads)
-    alibi_bias = alibi_bias * (1. / (2**m.view(1, n_heads, 1, 1)))
-    return alibi_bias
+    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}

blocks.py

@@ -0,0 +1,41 @@
+"""GPT Blocks used for the GPT Model."""
+from typing import Dict, Optional, Tuple
+import torch
+import torch.nn as nn
+from .attention import ATTN_CLASS_REGISTRY
+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):
+        del kwargs
+        super().__init__()
+        norm_class = NORM_CLASS_REGISTRY[norm_type.lower()]
+        attn_class = ATTN_CLASS_REGISTRY[attn_config['attn_type']]
+        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.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]]]:
+        a = self.norm_1(x)
+        (b, _, past_key_value) = self.attn(a, past_key_value=past_key_value, attn_bias=attn_bias, attention_mask=attention_mask, is_causal=is_causal)
+        x = x + self.resid_attn_dropout(b)
+        m = self.norm_2(x)
+        n = self.ffn(m)
+        x = x + self.resid_ffn_dropout(n)
+        return (x, past_key_value)

config.json

@@ -1,45 +1,51 @@
 {
-  "_name_or_path": "replit/replit-code-v1-3b",
-  "alibi": true,
-  "alibi_bias_max": 8,
   "architectures": [
-    "ReplitLM"
+    "MPTForCausalLM"
   ],
-  "attn_clip_qkv": null,
-  "attn_impl": "torch",
-  "attn_pdrop": 0,
-  "attn_qk_ln": false,
-  "attn_uses_sequence_id": false,
+  "attn_config": {
+    "alibi": true,
+    "alibi_bias_max": 8,
+    "attn_impl": "torch",
+    "attn_pdrop": 0,
+    "attn_type": "multihead_attention",
+    "attn_uses_sequence_id": false,
+    "clip_qkv": null,
+    "prefix_lm": false,
+    "qk_ln": false,
+    "softmax_scale": null
+  },
   "auto_map": {
-    "AutoConfig": "configuration_replit_lm.ReplitLMConfig",
-    "AutoModelForCausalLM": "replit_lm.ReplitLM"
+    "AutoConfig": "configuration_mpt.MPTConfig",
+    "AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
   },
   "d_model": 2560,
-  "emb_init_std": null,
-  "emb_init_uniform_lim": null,
   "emb_pdrop": 0,
   "embedding_fraction": 1.0,
-  "fan_mode": "fan_in",
+  "expansion_ratio": 4,
+  "init_config": {
+    "emb_init_std": null,
+    "emb_init_uniform_lim": null,
+    "fan_mode": "fan_in",
+    "init_div_is_residual": true,
+    "init_gain": 0,
+    "init_nonlinearity": "relu",
+    "init_std": 0.02,
+    "name": "kaiming_normal_",
+    "verbose": 0
+  },
   "init_device": "cpu",
-  "init_div_is_residual": true,
-  "init_gain": 0,
-  "init_nonlinearity": "relu",
-  "init_std": 0.02,
+  "learned_pos_emb": true,
   "logit_scale": null,
-  "low_precision_layernorm": true,
   "max_seq_len": 2048,
-  "mlp_ratio": 4,
-  "model_type": "replit_lm",
+  "model_type": "mpt",
   "n_heads": 32,
   "n_layers": 32,
   "no_bias": true,
-  "param_init_fn": "kaiming_normal_",
-  "prefix_lm": false,
+  "norm_type": "low_precision_layernorm",
   "resid_pdrop": 0,
-  "softmax_scale": null,
   "tokenizer_name": "replit/replit-code-v1-3b",
   "torch_dtype": "float32",
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.28.1",
   "use_cache": false,
   "verbose": 0,
   "vocab_size": 32768

configuration_mpt.py

@@ -0,0 +1,118 @@
+"""A HuggingFace-style model configuration."""
+from typing import 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}
+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):
+        """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.
+            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_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.
+                clip_qkv (Optional[float]): If not None, clip the queries, keys, and values in the attention layer to
+                    this value.
+                softmax_scale (Optional[float]): If not None, scale the softmax in the attention layer by this value. If None,
+                    use the default scale of ``1/sqrt(d_keys)``.
+                prefix_lm (Optional[bool]): Whether the model should operate as a Prefix LM. This requires passing an
+                    extra `prefix_mask` argument which indicates which tokens belong to the prefix. Tokens in the prefix
+                    can attend to one another bi-directionally. Tokens outside the prefix use causal attention.
+                attn_uses_sequence_id (Optional[bool]): Whether to restrict attention to tokens that have the same sequence_id.
+                    When the model is in `train` mode, this requires passing an extra `sequence_id` argument which indicates
+                    which sub-sequence each token belongs to.
+                    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.
+            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_',
+                    'kaiming_uniform_', 'kaiming_normal_', 'neox_init_', 'small_init_', 'xavier_uniform_', or
+                    'xavier_normal_'. These mimic the parameter initialization methods in PyTorch.
+                init_div_is_residual (Union[int, float, str, bool]): Value to divide initial weights by if ``module._is_residual`` is True.
+                emb_init_std (Optional[float]): The standard deviation of the normal distribution used to initialize the embedding layer.
+                emb_init_uniform_lim (Optional[Union[Tuple[float, float], float]]): The lower and upper limits of the uniform distribution
+                    used to initialize the embedding layer. Mutually exclusive with ``emb_init_std``.
+                init_std (float): The standard deviation of the normal distribution used to initialize the model,
+                    if using the baseline_ parameter initialization scheme.
+                init_gain (float): The gain to use for parameter initialization with kaiming or xavier initialization schemes.
+                fan_mode (str): The fan mode to use for parameter initialization with kaiming initialization schemes.
+                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
+        """
+        self.d_model = d_model
+        self.n_heads = n_heads
+        self.n_layers = n_layers
+        self.expansion_ratio = expansion_ratio
+        self.max_seq_len = max_seq_len
+        self.vocab_size = vocab_size
+        self.resid_pdrop = resid_pdrop
+        self.emb_pdrop = emb_pdrop
+        self.learned_pos_emb = learned_pos_emb
+        self.attn_config = attn_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
+        if 'name' in kwargs:
+            del kwargs['name']
+        if 'loss_fn' in kwargs:
+            del kwargs['loss_fn']
+        super().__init__(**kwargs)
+        self._validate_config()
+
+    def _set_config_defaults(self, config, config_defaults):
+        for (k, v) in config_defaults.items():
+            if k not in config:
+                config[k] = v
+        return config
+
+    def _validate_config(self):
+        self.attn_config = self._set_config_defaults(self.attn_config, attn_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')
+        if any((prob < 0 or prob > 1 for prob in [self.attn_config['attn_pdrop'], self.resid_pdrop, self.emb_pdrop])):
+            raise ValueError("self.attn_config['attn_pdrop'], resid_pdrop, emb_pdrop are probabilities and must be between 0 and 1")
+        if self.attn_config['attn_impl'] not in ['torch', 'flash', 'triton']:
+            raise ValueError(f"Unknown attn_impl={self.attn_config['attn_impl']}")
+        if self.attn_config['prefix_lm'] and self.attn_config['attn_impl'] not in ['torch', 'triton']:
+            raise NotImplementedError('prefix_lm only implemented with torch and triton attention.')
+        if self.attn_config['alibi'] and self.attn_config['attn_impl'] not in ['torch', 'triton']:
+            raise NotImplementedError('alibi only implemented with torch and triton attention.')
+        if self.attn_config['attn_uses_sequence_id'] and self.attn_config['attn_impl'] not in ['torch', 'triton']:
+            raise NotImplementedError('attn_uses_sequence_id only implemented with torch and triton attention.')
+        if self.embedding_fraction > 1 or self.embedding_fraction <= 0:
+            raise ValueError('model.embedding_fraction must be between 0 (exclusive) and 1 (inclusive)!')
+        if isinstance(self.logit_scale, str) and self.logit_scale != 'inv_sqrt_d_model':
+            raise ValueError(f"self.logit_scale={self.logit_scale!r} is not recognized as an option; use numeric value or 'inv_sqrt_d_model'.")
+        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.')

generation_config.json

@@ -1,5 +1,5 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.27.4",
+  "transformers_version": "4.28.1",
   "use_cache": false
 }

hf_prefixlm_converter.py

@@ -0,0 +1,415 @@
+"""Converts Huggingface Causal LM to Prefix LM.
+
+Conversion does lightweight surgery on a HuggingFace
+Causal LM to convert it to a Prefix LM.
+
+Prefix LMs accepts a `bidirectional_mask` input in `forward`
+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
+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
+from transformers.models.bloom.modeling_bloom import _make_causal_mask as _make_causal_mask_bloom
+from transformers.models.bloom.modeling_bloom import logging
+from transformers.models.gpt2.modeling_gpt2 import GPT2LMHeadModel
+from transformers.models.gpt_neo.modeling_gpt_neo import GPTNeoForCausalLM
+from transformers.models.gpt_neox.modeling_gpt_neox import GPTNeoXForCausalLM
+from transformers.models.gptj.modeling_gptj import GPTJForCausalLM
+from transformers.models.opt.modeling_opt import OPTForCausalLM
+from transformers.models.opt.modeling_opt import _expand_mask as _expand_mask_opt
+from transformers.models.opt.modeling_opt import _make_causal_mask as _make_causal_mask_opt
+logger = logging.get_logger(__name__)
+_SUPPORTED_GPT_MODELS = (GPT2LMHeadModel, GPTJForCausalLM, GPTNeoForCausalLM, GPTNeoXForCausalLM)
+CAUSAL_GPT_TYPES = Union[GPT2LMHeadModel, GPTJForCausalLM, GPTNeoForCausalLM, GPTNeoXForCausalLM]
+
+def _convert_gpt_causal_lm_to_prefix_lm(model: CAUSAL_GPT_TYPES) -> CAUSAL_GPT_TYPES:
+    """Converts a GPT-style Causal LM to a Prefix LM.
+
+    Supported HuggingFace model classes:
+        - `GPT2LMHeadModel`
+        - `GPTNeoForCausalLM`
+        - `GPTNeoXForCausalLM`
+        - `GPTJForCausalLM`
+
+    See `convert_hf_causal_lm_to_prefix_lm` for more details.
+    """
+    if hasattr(model, '_prefix_lm_converted'):
+        return model
+    assert isinstance(model, _SUPPORTED_GPT_MODELS)
+    assert model.config.add_cross_attention == False, 'Only supports GPT-style decoder-only models'
+
+    def _get_attn_modules(model: CAUSAL_GPT_TYPES) -> List[torch.nn.Module]:
+        """Helper that gets a list of the model's attention modules.
+
+        Each module has a `bias` buffer used for causal masking. The Prefix LM
+        conversion adds logic to dynamically manipulate these biases to support
+        Prefix LM attention masking.
+        """
+        attn_modules = []
+        if isinstance(model, GPTNeoXForCausalLM):
+            blocks = model.gpt_neox.layers
+        else:
+            blocks = model.transformer.h
+        for block in blocks:
+            if isinstance(model, GPTNeoForCausalLM):
+                if block.attn.attention_type != 'global':
+                    continue
+                attn_module = block.attn.attention
+            elif isinstance(model, GPTNeoXForCausalLM):
+                attn_module = block.attention
+            else:
+                attn_module = block.attn
+            attn_modules.append(attn_module)
+        return attn_modules
+    setattr(model, '_original_forward', getattr(model, 'forward'))
+    setattr(model, '_original_generate', getattr(model, 'generate'))
+
+    def forward(self: CAUSAL_GPT_TYPES, input_ids: Optional[torch.LongTensor]=None, past_key_values: Optional[Tuple[Tuple[torch.Tensor]]]=None, attention_mask: Optional[torch.FloatTensor]=None, bidirectional_mask: Optional[torch.Tensor]=None, token_type_ids: Optional[torch.LongTensor]=None, position_ids: Optional[torch.LongTensor]=None, head_mask: Optional[torch.FloatTensor]=None, inputs_embeds: Optional[torch.FloatTensor]=None, labels: 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):
+        """Wraps original forward to enable PrefixLM attention."""
+
+        def call_og_forward():
+            if isinstance(self, GPTNeoXForCausalLM):
+                return self._original_forward(input_ids=input_ids, past_key_values=past_key_values, attention_mask=attention_mask, head_mask=head_mask, inputs_embeds=inputs_embeds, labels=labels, use_cache=use_cache, output_attentions=output_attentions, output_hidden_states=output_hidden_states, return_dict=return_dict)
+            else:
+                return self._original_forward(input_ids=input_ids, past_key_values=past_key_values, attention_mask=attention_mask, token_type_ids=token_type_ids, position_ids=position_ids, head_mask=head_mask, inputs_embeds=inputs_embeds, labels=labels, use_cache=use_cache, output_attentions=output_attentions, output_hidden_states=output_hidden_states, return_dict=return_dict)
+        if bidirectional_mask is None:
+            return call_og_forward()
+        assert isinstance(bidirectional_mask, torch.Tensor)
+        attn_modules = _get_attn_modules(model)
+        (b, s) = bidirectional_mask.shape
+        max_length = attn_modules[0].bias.shape[-1]
+        if s > max_length:
+            raise ValueError(f'bidirectional_mask sequence length (={s}) exceeds the ' + f'max length allowed by the model ({max_length}).')
+        assert s <= max_length
+        if s < max_length:
+            pad = torch.zeros((int(b), int(max_length - s)), dtype=bidirectional_mask.dtype, device=bidirectional_mask.device)
+            bidirectional_mask = torch.cat([bidirectional_mask, pad], dim=1)
+        bidirectional = bidirectional_mask.unsqueeze(1).unsqueeze(1)
+        for attn_module in attn_modules:
+            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]):
+        """Wraps original generate to enable PrefixLM attention."""
+        attn_modules = _get_attn_modules(model)
+        for attn_module in attn_modules:
+            attn_module.bias.data[:] = 1
+        output = self._original_generate(*args, **kwargs)
+        for attn_module in attn_modules:
+            attn_module.bias.data = torch.tril(attn_module.bias.data[0, 0])[None, None]
+        return output
+    setattr(model, 'forward', MethodType(forward, model))
+    setattr(model, 'generate', MethodType(generate, model))
+    setattr(model, '_prefix_lm_converted', True)
+    return model
+
+def _convert_bloom_causal_lm_to_prefix_lm(model: BloomForCausalLM) -> BloomForCausalLM:
+    """Converts a BLOOM Causal LM to a Prefix LM.
+
+    Supported HuggingFace model classes:
+        - `BloomForCausalLM`
+
+    See `convert_hf_causal_lm_to_prefix_lm` for more details.
+    """
+    if hasattr(model, '_prefix_lm_converted'):
+        return model
+    assert isinstance(model, BloomForCausalLM)
+    assert model.config.add_cross_attention == False, 'Only supports BLOOM decoder-only models'
+
+    def _prepare_attn_mask(self: BloomModel, attention_mask: torch.Tensor, bidirectional_mask: Optional[torch.Tensor], input_shape: Tuple[int, int], past_key_values_length: int) -> torch.BoolTensor:
+        combined_attention_mask = None
+        device = attention_mask.device
+        (_, src_length) = input_shape
+        if src_length > 1:
+            combined_attention_mask = _make_causal_mask_bloom(input_shape, device=device, past_key_values_length=past_key_values_length)
+            if bidirectional_mask is not None:
+                assert attention_mask.shape == bidirectional_mask.shape
+                expanded_bidirectional_mask = _expand_mask_bloom(bidirectional_mask, tgt_length=src_length)
+                combined_attention_mask = torch.logical_and(combined_attention_mask, expanded_bidirectional_mask)
+        expanded_attn_mask = _expand_mask_bloom(attention_mask, tgt_length=src_length)
+        combined_attention_mask = expanded_attn_mask if combined_attention_mask is None else expanded_attn_mask | combined_attention_mask
+        return combined_attention_mask
+
+    def _build_alibi_tensor(self: BloomModel, batch_size: int, query_length: int, key_length: int, dtype: torch.dtype, device: torch.device) -> torch.Tensor:
+        num_heads = self.config.n_head
+        closest_power_of_2 = 2 ** math.floor(math.log2(num_heads))
+        base = torch.tensor(2 ** (-2 ** (-(math.log2(closest_power_of_2) - 3))), device=device, dtype=torch.float32)
+        powers = torch.arange(1, 1 + closest_power_of_2, device=device, dtype=torch.int32)
+        slopes = torch.pow(base, powers)
+        if closest_power_of_2 != num_heads:
+            extra_base = torch.tensor(2 ** (-2 ** (-(math.log2(2 * closest_power_of_2) - 3))), device=device, dtype=torch.float32)
+            num_remaining_heads = min(closest_power_of_2, num_heads - closest_power_of_2)
+            extra_powers = torch.arange(1, 1 + 2 * num_remaining_heads, 2, device=device, dtype=torch.int32)
+            slopes = torch.cat([slopes, torch.pow(extra_base, extra_powers)], dim=0)
+        qa = torch.arange(query_length, device=device, dtype=torch.int32).view(-1, 1)
+        ka = torch.arange(key_length, device=device, dtype=torch.int32).view(1, -1)
+        diffs = qa - ka + key_length - query_length
+        diffs = -diffs.abs()
+        alibi = slopes.view(1, num_heads, 1, 1) * diffs.view(1, 1, query_length, key_length)
+        alibi = alibi.expand(batch_size, -1, -1, -1).reshape(-1, query_length, key_length)
+        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]:
+        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:
+            raise ValueError(f'Got unexpected arguments: {deprecated_arguments}')
+        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+        output_hidden_states = output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        use_cache = use_cache if use_cache is not None else self.config.use_cache
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+        if input_ids is not None and inputs_embeds is not None:
+            raise ValueError('You cannot specify both input_ids and inputs_embeds at the same time')
+        elif input_ids is not None:
+            (batch_size, seq_length) = input_ids.shape
+        elif inputs_embeds is not None:
+            (batch_size, seq_length, _) = inputs_embeds.shape
+        else:
+            raise ValueError('You have to specify either input_ids or inputs_embeds')
+        if past_key_values is None:
+            past_key_values = tuple([None] * len(self.h))
+        head_mask = self.get_head_mask(head_mask, self.config.n_layer)
+        if inputs_embeds is None:
+            inputs_embeds = self.word_embeddings(input_ids)
+        hidden_states = self.word_embeddings_layernorm(inputs_embeds)
+        presents = () if use_cache else None
+        all_self_attentions = () if output_attentions else None
+        all_hidden_states = () if output_hidden_states else None
+        seq_length_with_past = seq_length
+        past_key_values_length = 0
+        if past_key_values[0] is not None:
+            tmp = past_key_values[0][0]
+            past_key_values_length = tmp.shape[2]
+            seq_length_with_past = seq_length_with_past + past_key_values_length
+        if attention_mask is None:
+            attention_mask = torch.ones((batch_size, seq_length_with_past), device=hidden_states.device)
+        else:
+            attention_mask = attention_mask.to(hidden_states.device)
+        alibi = self._build_alibi_tensor(batch_size=batch_size, query_length=seq_length, key_length=seq_length_with_past, dtype=hidden_states.dtype, device=hidden_states.device)
+        causal_mask = self._prepare_attn_mask(attention_mask, bidirectional_mask, input_shape=(batch_size, seq_length), past_key_values_length=past_key_values_length)
+        for (i, (block, layer_past)) in enumerate(zip(self.h, past_key_values)):
+            if output_hidden_states:
+                hst = (hidden_states,)
+                all_hidden_states = all_hidden_states + hst
+            if self.gradient_checkpointing and self.training:
+                if use_cache:
+                    logger.warning('`use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`...')
+                    use_cache = False
+
+                def create_custom_forward(module):
+
+                    def custom_forward(*inputs):
+                        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])
+            else:
+                outputs = block(hidden_states, layer_past=layer_past, attention_mask=causal_mask, head_mask=head_mask[i], use_cache=use_cache, output_attentions=output_attentions, alibi=alibi)
+            hidden_states = outputs[0]
+            if use_cache is True:
+                presents = presents + (outputs[1],)
+            if output_attentions:
+                oa = (outputs[2 if use_cache else 1],)
+                all_self_attentions = all_self_attentions + oa
+        hidden_states = self.ln_f(hidden_states)
+        if output_hidden_states:
+            hst = (hidden_states,)
+            all_hidden_states = all_hidden_states + hst
+        if not return_dict:
+            return tuple((v for v in [hidden_states, presents, all_hidden_states, all_self_attentions] if v is not None))
+        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))
+    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]:
+        """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)
+        if len(deprecated_arguments) > 0:
+            raise ValueError(f'Got unexpected arguments: {deprecated_arguments}')
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+        transformer_outputs = self.transformer(input_ids, past_key_values=past_key_values, attention_mask=attention_mask, bidirectional_mask=bidirectional_mask, head_mask=head_mask, inputs_embeds=inputs_embeds, use_cache=use_cache, output_attentions=output_attentions, output_hidden_states=output_hidden_states, return_dict=return_dict)
+        hidden_states = transformer_outputs[0]
+        lm_logits = self.lm_head(hidden_states)
+        loss = None
+        if labels is not None:
+            shift_logits = lm_logits[..., :-1, :].contiguous()
+            shift_labels = labels[..., 1:].contiguous()
+            (batch_size, seq_length, vocab_size) = shift_logits.shape
+            loss_fct = CrossEntropyLoss()
+            loss = loss_fct(shift_logits.view(batch_size * seq_length, vocab_size), shift_labels.view(batch_size * seq_length))
+        if not return_dict:
+            output = (lm_logits,) + transformer_outputs[1:]
+            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:
+        if past:
+            input_ids = input_ids[:, -1].unsqueeze(-1)
+            bidirectional_mask = None
+            if past[0][0].shape[0] == input_ids.shape[0]:
+                past = self._convert_to_bloom_cache(past)
+        else:
+            bidirectional_mask = torch.ones_like(input_ids)
+        return {'input_ids': input_ids, 'past_key_values': past, 'use_cache': True, 'attention_mask': attention_mask, 'bidirectional_mask': bidirectional_mask}
+    setattr(model, 'forward', MethodType(forward, model))
+    setattr(model, 'prepare_inputs_for_generation', MethodType(prepare_inputs_for_generation, model))
+    setattr(model, '_prefix_lm_converted', True)
+    return model
+
+def _convert_opt_causal_lm_to_prefix_lm(model: OPTForCausalLM) -> OPTForCausalLM:
+    """Converts an OPT Causal LM to a Prefix LM.
+
+    Supported HuggingFace model classes:
+        - `OPTForCausalLM`
+
+    See `convert_hf_causal_lm_to_prefix_lm` for more details.
+    """
+    if hasattr(model, '_prefix_lm_converted'):
+        return model
+    assert isinstance(model, OPTForCausalLM)
+    assert model.config.add_cross_attention == False, 'Only supports OPT decoder-only models'
+    setattr(model, '_original_forward', getattr(model, 'forward'))
+    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):
+        combined_attention_mask = None
+        if input_shape[-1] > 1:
+            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.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:
+            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
+    setattr(model.model.decoder, '_prepare_decoder_attention_mask', MethodType(_prepare_decoder_attention_mask, model.model.decoder))
+
+    def forward(self: OPTForCausalLM, input_ids: Optional[torch.LongTensor]=None, attention_mask: Optional[torch.Tensor]=None, bidirectional_mask: Optional[torch.ByteTensor]=None, head_mask: Optional[torch.Tensor]=None, past_key_values: Optional[List[torch.FloatTensor]]=None, inputs_embeds: Optional[torch.FloatTensor]=None, labels: 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):
+
+        def call_og_forward():
+            return self._original_forward(input_ids=input_ids, attention_mask=attention_mask, head_mask=head_mask, past_key_values=past_key_values, inputs_embeds=inputs_embeds, labels=labels, use_cache=use_cache, output_attentions=output_attentions, output_hidden_states=output_hidden_states, return_dict=return_dict)
+        if bidirectional_mask is None:
+            return call_og_forward()
+        self.model.decoder.bidirectional_mask = bidirectional_mask
+        try:
+            outputs = call_og_forward()
+        except:
+            self.model.decoder.bidirectional_mask = None
+            raise
+        self.model.decoder.bidirectional_mask = None
+        return outputs
+
+    def generate(self: OPTForCausalLM, *args: tuple, **kwargs: Dict[str, Any]):
+        """Wraps original generate to enable PrefixLM-style attention."""
+        self.model.decoder.bidirectional_mask = 'g'
+        try:
+            output = self._original_generate(*args, **kwargs)
+        except:
+            self.model.decoder.bidirectional_mask = None
+            raise
+        self.model.decoder.bidirectional_mask = None
+        return output
+    setattr(model, 'forward', MethodType(forward, model))
+    setattr(model, 'generate', MethodType(generate, model))
+    setattr(model, '_prefix_lm_converted', True)
+    return model
+_SUPPORTED_HF_MODELS = _SUPPORTED_GPT_MODELS + (BloomForCausalLM, OPTForCausalLM)
+CAUSAL_LM_TYPES = Union[GPT2LMHeadModel, GPTJForCausalLM, GPTNeoForCausalLM, GPTNeoXForCausalLM, BloomForCausalLM, OPTForCausalLM]
+
+def convert_hf_causal_lm_to_prefix_lm(model: CAUSAL_LM_TYPES) -> CAUSAL_LM_TYPES:
+    """Converts a HuggingFace Causal LM to a Prefix LM.
+
+    Supported HuggingFace model classes:
+        - `GPT2LMHeadModel`
+        - `GPTNeoForCausalLM`
+        - `GPTNeoXForCausalLM`
+        - `GPTJForCausalLM`
+        - `BloomForCausalLM`
+        - `OPTForCausalLM`
+
+    Conversion to a Prefix LM is done by modifying the `forward` method, and possibly also the
+    `generate` method and/or select underlying methods depending on the model class.
+
+    These changes preserve the model API, but add a new input to `forward`: "bidirectional_mask".
+
+    Notes on training:
+        To actually train the converted model as a Prefix LM, training batches will need to indicate
+        the prefix/target structure by including `bidirectional_mask` as part of the batch inputs.
+
+        **This is not a standard input and requires custom layers either within or after your dataloader.**
+
+        In addition to adding `bidirectional_mask` to the batch, this custom code should modify `labels`
+        such that `batch['labels'][batch['bidirectional_mask'] == 1] == -100`.
+        That is, the prefix portion of the sequence should not generate any loss. Loss should only be
+        generated by the target portion of the sequence.
+
+    Notes on `GPTNeoForCausalLM`:
+        To simplify the implementation, "global" and "local" attention layers are handled differently.
+        For "global" layers, we handle conversion as described above. For "local" layers, which use a
+        causal attention mask within a restricted local window, we do not alter the masking.
+
+    Notes on `forward` method conversion:
+        After conversion, the `forward` method will handle a new input, `bidirectional_mask`,
+        which should be a [batch_size, seq_length] byte tensor, where 1 indicates token positions
+        belonging to the prefix (prefix tokens can attend to one another bidirectionally), and
+        0 indicates token positions belonging to the target.
+
+        The new `forward` method will incorporate `bidirectional_mask` (if supplied) into the existing
+        causal mask, call the original `forward` method, and (if the causal mask is a buffer) reset
+        the causal masks before returning the result.
+
+    Notes on `generate` method conversion:
+        After conversion, the `generate` method will have the same signature but will internally
+        convert all causal masks to be purely bidirectional, call the original `generate` method, and
+        (where appropriate) reset the causal masks before returning the result.
+
+        This works thanks to the logic of the HuggingFace `generate` API, which first encodes the token
+        "prompt" passed to `generate` (which is treated as the prefix) and then sequentially generates
+        each new token. Encodings are cached as generation happens, so all prefix tokens can attend to one
+        another (as expected in a Prefix LM) and generated tokens can only attend to prefix tokens and
+        previously-generated tokens (also as expected in a Prefix LM).
+
+    To preserve the API, the original methods are renamed to `_original_forward` and
+    `_original_generate`, and replaced with new `forward` and `generate` methods that wrap
+    them, respectively. Although implementation details vary by model class.
+    """
+    if isinstance(model, _SUPPORTED_GPT_MODELS):
+        return _convert_gpt_causal_lm_to_prefix_lm(model)
+    elif isinstance(model, BloomForCausalLM):
+        return _convert_bloom_causal_lm_to_prefix_lm(model)
+    elif isinstance(model, OPTForCausalLM):
+        return _convert_opt_causal_lm_to_prefix_lm(model)
+    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]):
+    """Attempts to add bidirectional_mask to batch if missing.
+
+    Raises:
+        KeyError if bidirectional_mask is missing and can't be inferred
+    """
+    if 'bidirectional_mask' not in batch:
+        if batch.get('mode', None) == 'icl_task':
+            batch['bidirectional_mask'] = batch['attention_mask'].clone()
+            for (i, continuation_indices) in enumerate(batch['continuation_indices']):
+                batch['bidirectional_mask'][i, continuation_indices] = 0
+        elif 'labels' in batch and 'attention_mask' in batch:
+            batch['bidirectional_mask'] = torch.logical_and(torch.eq(batch['attention_mask'], 1), torch.eq(batch['labels'], -100)).type_as(batch['attention_mask'])
+        else:
+            raise KeyError('No bidirectional_mask in batch and not sure how to construct one.')

meta_init_context.py

@@ -0,0 +1,94 @@
+from contextlib import contextmanager
+import torch
+import torch.nn as nn
+
+@contextmanager
+def init_empty_weights(include_buffers: bool=False):
+    """Meta initialization context manager.
+
+    A context manager under which models are initialized with all parameters
+    on the meta device, therefore creating an empty model. Useful when just
+    initializing the model would blow the available RAM.
+
+    Args:
+        include_buffers (`bool`, *optional*, defaults to `False`): Whether or
+            not to also put all buffers on the meta device while initializing.
+
+    Example:
+    ```python
+    import torch.nn as nn
+
+    # Initialize a model with 100 billions parameters in no time and without using any RAM.
+    with init_empty_weights():
+        tst = nn.Sequential(*[nn.Linear(10000, 10000) for _ in range(1000)])
+    ```
+
+    <Tip warning={true}>
+
+    Any model created under this context manager has no weights. As such you can't do something like
+    `model.to(some_device)` with it. To load weights inside your empty model, see [`load_checkpoint_and_dispatch`].
+
+    </Tip>
+    """
+    with init_on_device(torch.device('meta'), include_buffers=include_buffers) as f:
+        yield f
+
+@contextmanager
+def init_on_device(device: torch.device, include_buffers: bool=False):
+    """Device initialization context manager.
+
+    A context manager under which models are initialized with all parameters
+    on the specified device.
+
+    Args:
+        device (`torch.device`): Device to initialize all parameters on.
+        include_buffers (`bool`, *optional*, defaults to `False`): Whether or
+            not to also put all buffers on the meta device while initializing.
+
+    Example:
+    ```python
+    import torch.nn as nn
+
+    with init_on_device(device=torch.device("cuda")):
+        tst = nn.Liner(100, 100)  # on `cuda` device
+    ```
+    """
+    old_register_parameter = nn.Module.register_parameter
+    if include_buffers:
+        old_register_buffer = nn.Module.register_buffer
+
+    def register_empty_parameter(module, name, param):
+        old_register_parameter(module, 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)
+    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 wrapper(*args, **kwargs):
+            kwargs['device'] = device
+            return fn(*args, **kwargs)
+        return wrapper
+    try:
+        nn.Module.register_parameter = register_empty_parameter
+        if include_buffers:
+            nn.Module.register_buffer = register_empty_buffer
+        for torch_function_name in tensor_constructors_to_patch.keys():
+            setattr(torch, torch_function_name, patch_tensor_constructor(getattr(torch, torch_function_name)))
+        yield
+    finally:
+        nn.Module.register_parameter = old_register_parameter
+        if include_buffers:
+            nn.Module.register_buffer = old_register_buffer
+        for (torch_function_name, old_torch_function) in tensor_constructors_to_patch.items():
+            setattr(torch, torch_function_name, old_torch_function)