Upload 7 files

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

@@ -0,0 +1,300 @@
+"""Attention layers."""
+import math
+import warnings
+from typing import Optional
+import torch
+import torch.nn as nn
+from einops import rearrange
+from packaging import version
+from torch import nn
+from .norm import LPLayerNorm
+
+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('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, 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):
+    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:
+        if len(past_key_value) != 0:
+            k = torch.cat([past_key_value[0], k], dim=3)
+            v = torch.cat([past_key_value[1], v], dim=2)
+        past_key_value = (k, v)
+    (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:
+        _s_q = max(0, attn_bias.size(2) - s_q)
+        _s_k = max(0, attn_bias.size(3) - s_k)
+        attn_bias = attn_bias[:, :, _s_q:, _s_k:]
+        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
+    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.')
+        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 = causal_mask.tril()
+        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 = torch.softmax(attn_weight, dim=-1)
+    if dropout_p:
+        attn_weight = torch.nn.functional.dropout(attn_weight, p=dropout_p, training=training, inplace=True)
+    out = attn_weight.to(v.dtype).matmul(v)
+    out = rearrange(out, 'b h s d -> b s (h d)')
+    if needs_weights:
+        return (out, attn_weight, past_key_value)
+    return (out, None, past_key_value)
+
+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={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):
+    try:
+        from flash_attn import bert_padding, flash_attn_interface
+    except:
+        raise RuntimeError('Please install flash-attn==1.0.3.post0')
+    check_valid_inputs(query, key, value)
+    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:
+        _s_q = max(0, attn_bias.size(2) - query.size(1))
+        _s_k = max(0, attn_bias.size(3) - key.size(1))
+        attn_bias = attn_bias[:, :, _s_q:, _s_k:]
+    if attn_bias is not None:
+        raise NotImplementedError(f'attn_bias not implemented for flash attn.')
+    (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 = 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)
+    (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, 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):
+    try:
+        from .flash_attn_triton import flash_attn_func
+    except:
+        _installed = False
+        if version.parse(torch.__version__) < version.parse('2.0.0'):
+            _installed = True
+            try:
+                from flash_attn.flash_attn_triton import flash_attn_func
+            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.')
+    check_valid_inputs(query, key, value)
+    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:
+        _s_q = max(0, attn_bias.size(2) - query.size(1))
+        _s_k = max(0, attn_bias.size(3) - key.size(1))
+        attn_bias = attn_bias[:, :, _s_q:, _s_k:]
+    if dropout_p:
+        raise NotImplementedError(f'Dropout not implemented for attn_impl: triton.')
+    if needs_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]
+        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)
+    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))
+    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.
+
+    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.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)
+        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
+            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 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)
+        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)
+        return (self.out_proj(context), attn_weights, past_key_value)
+
+class MultiQueryAttention(nn.Module):
+    """Multi-Query self attention.
+
+    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 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)
+
+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']:
+        if alibi:
+            if (prefix_lm or not causal) or use_sequence_id:
+                return (1, n_heads, seq_len, seq_len)
+            return (1, n_heads, 1, seq_len)
+        elif prefix_lm or use_sequence_id:
+            return (1, 1, seq_len, seq_len)
+        return None
+    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):
+    if attn_impl == 'flash':
+        return None
+    elif attn_impl in ['torch', 'triton']:
+        if alibi:
+            (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={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:
+        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)
+    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, 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)
+        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, attn_weights, past_key_value)

custom_embedding.py

@@ -0,0 +1,11 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch import Tensor
+
+class SharedEmbedding(nn.Embedding):
+
+    def forward(self, input: Tensor, unembed: bool=False) -> Tensor:
+        if unembed:
+            return F.linear(input, self.weight)
+        return super().forward(input)

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)

norm.py

@@ -0,0 +1,56 @@
+import torch
+
+def _cast_if_autocast_enabled(tensor):
+    if torch.is_autocast_enabled():
+        if tensor.device.type == 'cuda':
+            dtype = torch.get_autocast_gpu_dtype()
+        elif tensor.device.type == 'cpu':
+            dtype = torch.get_autocast_cpu_dtype()
+        else:
+            raise NotImplementedError()
+        return tensor.to(dtype=dtype)
+    return tensor
+
+class LPLayerNorm(torch.nn.LayerNorm):
+
+    def __init__(self, normalized_shape, eps=1e-05, elementwise_affine=True, device=None, dtype=None):
+        super().__init__(normalized_shape=normalized_shape, eps=eps, elementwise_affine=elementwise_affine, device=device, dtype=dtype)
+
+    def forward(self, x):
+        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
+        downcast_bias = _cast_if_autocast_enabled(self.bias) if self.bias is not None else self.bias
+        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):
+    output = x * torch.rsqrt(x.pow(2).mean(-1, keepdim=True) + eps)
+    if weight is not None:
+        return output * weight
+    return output
+
+class RMSNorm(torch.nn.Module):
+
+    def __init__(self, normalized_shape, eps=1e-05, weight=True, dtype=None, device=None):
+        super().__init__()
+        self.eps = eps
+        if weight:
+            self.weight = torch.nn.Parameter(torch.ones(normalized_shape, dtype=dtype, device=device))
+        else:
+            self.register_parameter('weight', None)
+
+    def forward(self, x):
+        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):
+        super().__init__(normalized_shape=normalized_shape, eps=eps, weight=weight, dtype=dtype, device=device)
+
+    def forward(self, x):
+        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}

param_init_fns.py

@@ -0,0 +1,181 @@
+import math
+import warnings
+from collections.abc import Sequence
+from functools import partial
+from typing import Optional, Tuple, Union
+import torch
+from torch import nn
+from .norm import NORM_CLASS_REGISTRY
+
+def torch_default_param_init_fn_(module: nn.Module, verbose: int=0, **kwargs):
+    del kwargs
+    if verbose > 1:
+        warnings.warn(f"Initializing network using module's reset_parameters attribute")
+    if hasattr(module, 'reset_parameters'):
+        module.reset_parameters()
+
+def fused_init_helper_(module: nn.Module, init_fn_):
+    _fused = getattr(module, '_fused', None)
+    if _fused is None:
+        raise RuntimeError(f'Internal logic error')
+    (dim, splits) = _fused
+    splits = (0, *splits, module.weight.size(dim))
+    for (s, e) in zip(splits[:-1], splits[1:]):
+        slice_indices = [slice(None)] * module.weight.ndim
+        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):
+    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
+    elif init_div_is_residual is True:
+        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():
+        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 hasattr(module, '_fused'):
+            fused_init_helper_(module, init_fn_)
+        else:
+            init_fn_(module.weight)
+        if module.bias is not None:
+            torch.nn.init.zeros_(module.bias)
+        if init_div_is_residual is not False and getattr(module, '_is_residual', False):
+            with torch.no_grad():
+                module.weight.div_(div_is_residual)
+    elif isinstance(module, nn.Embedding):
+        if emb_init_std is not None:
+            std = emb_init_std
+            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):
+                if len(lim) > 2:
+                    raise ValueError(f'Uniform init requires a min and a max limit. User input: {lim}.')
+                if lim[0] == lim[1]:
+                    warnings.warn(f'Embedding layer initialized to {lim[0]}.')
+            else:
+                if lim == 0:
+                    warnings.warn(f'Embedding layer initialized to 0.')
+                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:
+            torch.nn.init.ones_(module.weight)
+        if hasattr(module, 'bias') and module.bias is not None:
+            torch.nn.init.zeros_(module.bias)
+    elif isinstance(module, nn.MultiheadAttention):
+        if module._qkv_same_embed_dim:
+            assert module.in_proj_weight is not None
+            assert module.q_proj_weight is None and module.k_proj_weight is None and (module.v_proj_weight is None)
+            assert d_model is not None
+            _d = d_model
+            splits = (0, _d, 2 * _d, 3 * _d)
+            for (s, e) in zip(splits[:-1], splits[1:]):
+                init_fn_(module.in_proj_weight[s:e])
+        else:
+            assert module.q_proj_weight is not None and module.k_proj_weight is not None and (module.v_proj_weight is not None)
+            assert module.in_proj_weight is None
+            init_fn_(module.q_proj_weight)
+            init_fn_(module.k_proj_weight)
+            init_fn_(module.v_proj_weight)
+        if module.in_proj_bias is not None:
+            torch.nn.init.zeros_(module.in_proj_bias)
+        if module.bias_k is not None:
+            torch.nn.init.zeros_(module.bias_k)
+        if module.bias_v is not None:
+            torch.nn.init.zeros_(module.bias_v)
+        init_fn_(module.out_proj.weight)
+        if init_div_is_residual is not False and getattr(module.out_proj, '_is_residual', False):
+            with torch.no_grad():
+                module.out_proj.weight.div_(div_is_residual)
+        if module.out_proj.bias is not None:
+            torch.nn.init.zeros_(module.out_proj.bias)
+    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):
+    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):
+    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)
+
+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):
+    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)
+
+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):
+    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)
+
+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):
+    """From section 2.3.1 of GPT-NeoX-20B:
+
+    An Open-Source AutoregressiveLanguage Model — Black et. al. (2022)
+    see https://github.com/EleutherAI/gpt-neox/blob/9610391ab319403cef079b438edd016a2443af54/megatron/model/init_functions.py#L151
+    and https://github.com/EleutherAI/gpt-neox/blob/main/megatron/model/transformer.py
+    """
+    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)
+
+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):
+    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)
+
+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):
+    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)
+
+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):
+    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)
+
+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):
+    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)
+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_}