Upload 9 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 +1,276 @@
+"""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
+
+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, 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=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
+    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}.')
+        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)
+    if is_causal:
+        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.matmul(v)
+    out = rearrange(out, 'b h s d -> b s (h d)')
+    if needs_weights:
+        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={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, 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 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)
+
+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
+    except:
+        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.')
+    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_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)
+
+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, 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
+            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`.')
+        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)
+        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)
+
+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, 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
+            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`.')
+        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)
+        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']:
+        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', 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, 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)

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)

modeling_mpt.py

@@ -0,0 +1,290 @@
+"""A simple, flexible implementation of a GPT model.
+
+Inspired by https://github.com/karpathy/minGPT/blob/master/mingpt/model.py
+"""
+import math
+import warnings
+from typing import List, Optional, Tuple, Union
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from transformers import PreTrainedModel, PreTrainedTokenizer, PreTrainedTokenizerFast
+from transformers.modeling_outputs import BaseModelOutputWithPast, CausalLMOutputWithPast
+from .attention import attn_bias_shape, build_attn_bias
+from .blocks import MPTBlock
+from .norm import NORM_CLASS_REGISTRY
+from .configuration_mpt import MPTConfig
+from .adapt_tokenizer import AutoTokenizerForMOD, adapt_tokenizer_for_denoising
+from .hf_prefixlm_converter import add_bidirectional_mask_if_missing, convert_hf_causal_lm_to_prefix_lm
+from .meta_init_context import init_empty_weights
+from .param_init_fns import MODEL_INIT_REGISTRY, generic_param_init_fn_
+Tokenizer = Union[PreTrainedTokenizer, PreTrainedTokenizerFast]
+
+class MPTPreTrainedModel(PreTrainedModel):
+    config_class = MPTConfig
+    base_model_prefix = 'model'
+
+class MPTModel(MPTPreTrainedModel):
+
+    def __init__(self, config: MPTConfig):
+        config._validate_config()
+        super().__init__(config)
+        self.attn_impl = config.attn_config['attn_impl']
+        self.prefix_lm = config.attn_config['prefix_lm']
+        self.attn_uses_sequence_id = config.attn_config['attn_uses_sequence_id']
+        self.alibi = config.attn_config['alibi']
+        self.alibi_bias_max = config.attn_config['alibi_bias_max']
+        if config.norm_type.lower() not in NORM_CLASS_REGISTRY.keys():
+            norm_options = ' | '.join(NORM_CLASS_REGISTRY.keys())
+            raise NotImplementedError(f'Requested norm type ({config.norm_type}) is not implemented within this repo (Options: {norm_options}).')
+        norm_class = NORM_CLASS_REGISTRY[config.norm_type.lower()]
+        self.embedding_fraction = config.embedding_fraction
+        self.wte = nn.Embedding(config.vocab_size, config.d_model, device=config.init_device)
+        if not self.alibi:
+            self.wpe = nn.Embedding(config.max_seq_len, config.d_model, device=config.init_device)
+        self.emb_drop = nn.Dropout(config.emb_pdrop)
+        self.blocks = nn.ModuleList([MPTBlock(device=config.init_device, **config.to_dict()) for _ in range(config.n_layers)])
+        self.norm_f = norm_class(config.d_model, device=config.init_device)
+        if config.init_device != 'meta':
+            self.apply(self.param_init_fn)
+        self.is_causal = not self.prefix_lm
+        self._attn_bias_initialized = False
+        self.attn_bias = None
+        self.attn_bias_shape = attn_bias_shape(self.attn_impl, config.n_heads, config.max_seq_len, self.alibi, prefix_lm=self.prefix_lm, causal=self.is_causal, use_sequence_id=self.attn_uses_sequence_id)
+        if config.no_bias:
+            for module in self.modules():
+                if hasattr(module, 'bias') and isinstance(module.bias, nn.Parameter):
+                    if config.verbose:
+                        warnings.warn(f'Removing bias ({module.bias}) from {module}.')
+                    module.register_parameter('bias', None)
+        if config.verbose and config.verbose > 2:
+            print(self)
+        if 'verbose' not in self.config.init_config:
+            self.config.init_config['verbose'] = self.config.verbose
+        if self.config.init_config['verbose'] > 1:
+            init_fn_name = self.config.init_config['name']
+            warnings.warn(f'Using {init_fn_name} initialization.')
+
+    def get_input_embeddings(self):
+        return self.wte
+
+    def set_input_embeddings(self, value):
+        self.wte = value
+
+    @torch.no_grad()
+    def _attn_bias(self, device, dtype, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None):
+        if not self._attn_bias_initialized:
+            if self.attn_bias_shape:
+                self.attn_bias = torch.zeros(self.attn_bias_shape, device=device, dtype=dtype)
+                self.attn_bias = build_attn_bias(self.attn_impl, self.attn_bias, self.config.n_heads, self.config.max_seq_len, causal=self.is_causal, alibi=self.alibi, alibi_bias_max=self.alibi_bias_max)
+            self._attn_bias_initialized = True
+        if self.attn_impl == 'flash':
+            return (self.attn_bias, attention_mask)
+        if self.attn_bias is not None:
+            self.attn_bias = self.attn_bias.to(dtype=dtype, device=device)
+        attn_bias = self.attn_bias
+        if self.prefix_lm:
+            assert isinstance(attn_bias, torch.Tensor)
+            assert isinstance(prefix_mask, torch.Tensor)
+            attn_bias = self._apply_prefix_mask(attn_bias, prefix_mask)
+        if self.attn_uses_sequence_id and sequence_id is not None:
+            assert isinstance(attn_bias, torch.Tensor)
+            attn_bias = self._apply_sequence_id(attn_bias, sequence_id)
+        if attention_mask is not None:
+            s_k = attention_mask.shape[-1]
+            if attn_bias is None:
+                attn_bias = torch.zeros((1, 1, 1, s_k), device=device, dtype=dtype)
+            else:
+                attn_bias = attn_bias[:, :, :, -s_k:]
+            if prefix_mask is not None and attention_mask.shape != prefix_mask.shape:
+                raise ValueError(f'attention_mask shape={attention_mask.shape} ' + f'and prefix_mask shape={prefix_mask.shape} are not equal.')
+            min_val = torch.finfo(attn_bias.dtype).min
+            attn_bias = attn_bias.masked_fill(~attention_mask.view(-1, 1, 1, s_k), min_val)
+        return (attn_bias, None)
+
+    def _apply_prefix_mask(self, attn_bias: torch.Tensor, prefix_mask: torch.Tensor):
+        (s_k, s_q) = attn_bias.shape[-2:]
+        if s_k != self.config.max_seq_len or s_q != self.config.max_seq_len:
+            raise ValueError('attn_bias does not match the expected shape. ' + f'The last two dimensions should both be {self.config.max_length} ' + f'but are {s_k} and {s_q}.')
+        seq_len = prefix_mask.shape[-1]
+        if seq_len > self.config.max_seq_len:
+            raise ValueError(f'prefix_mask sequence length cannot exceed max_seq_len={self.config.max_seq_len}')
+        attn_bias = attn_bias[..., :seq_len, :seq_len]
+        causal = torch.tril(torch.ones((seq_len, seq_len), dtype=torch.bool, device=prefix_mask.device)).view(1, 1, seq_len, seq_len)
+        prefix = prefix_mask.view(-1, 1, 1, seq_len)
+        cannot_attend = ~torch.logical_or(causal, prefix.bool())
+        min_val = torch.finfo(attn_bias.dtype).min
+        attn_bias = attn_bias.masked_fill(cannot_attend, min_val)
+        return attn_bias
+
+    def _apply_sequence_id(self, attn_bias: torch.Tensor, sequence_id: torch.LongTensor):
+        seq_len = sequence_id.shape[-1]
+        if seq_len > self.config.max_seq_len:
+            raise ValueError(f'sequence_id sequence length cannot exceed max_seq_len={self.config.max_seq_len}')
+        attn_bias = attn_bias[..., :seq_len, :seq_len]
+        cannot_attend = torch.logical_not(torch.eq(sequence_id.view(-1, seq_len, 1), sequence_id.view(-1, 1, seq_len))).unsqueeze(1)
+        min_val = torch.finfo(attn_bias.dtype).min
+        attn_bias = attn_bias.masked_fill(cannot_attend, min_val)
+        return attn_bias
+
+    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None):
+        return_dict = return_dict if return_dict is not None else self.config.return_dict
+        use_cache = use_cache if use_cache is not None else self.config.use_cache
+        if attention_mask is not None:
+            attention_mask = attention_mask.bool()
+        if prefix_mask is not None:
+            prefix_mask = prefix_mask.bool()
+        if not return_dict:
+            raise NotImplementedError('return_dict False is not implemented yet for MPT')
+        if output_attentions:
+            raise NotImplementedError('output_attentions is not implemented yet for MPT')
+        if attention_mask is not None and attention_mask[:, 0].sum() != attention_mask.shape[0] and self.training:
+            raise NotImplementedError('MPT does not support training with left padding.')
+        if self.prefix_lm and prefix_mask is None:
+            raise ValueError('prefix_mask is a required argument when MPT is configured with prefix_lm=True.')
+        if self.training:
+            if self.attn_uses_sequence_id and sequence_id is None:
+                raise ValueError('sequence_id is a required argument when MPT is configured with attn_uses_sequence_id=True ' + 'and the model is in train mode.')
+            elif self.attn_uses_sequence_id is False and sequence_id is not None:
+                warnings.warn('MPT received non-None input for `sequence_id` but is configured with attn_uses_sequence_id=False. ' + 'This input will be ignored. If you want the model to use `sequence_id`, set attn_uses_sequence_id to True.')
+        S = input_ids.size(1)
+        assert S <= self.config.max_seq_len, f'Cannot forward input with seq_len={S}, this model only supports seq_len<={self.config.max_seq_len}'
+        tok_emb = self.wte(input_ids)
+        if self.alibi:
+            x = tok_emb
+        else:
+            past_position = 0
+            if past_key_values is not None:
+                if len(past_key_values) != self.config.n_layers:
+                    raise ValueError(f'past_key_values must provide a past_key_value for each attention ' + f'layer in the network (len(past_key_values)={len(past_key_values)!r}; self.config.n_layers={self.config.n_layers!r}).')
+                past_position = past_key_values[0][0].size(1)
+            if S + past_position > self.config.max_seq_len:
+                raise ValueError(f'Cannot forward input with past sequence length {past_position} and current sequence length {S + 1}, this model only supports total sequence length <= {self.config.max_seq_len}.')
+            pos = torch.arange(past_position, S + past_position, dtype=torch.long, device=input_ids.device).unsqueeze(0)
+            if attention_mask is not None:
+                pos = torch.clamp(pos - torch.cumsum((~attention_mask).to(torch.int32), dim=1)[:, past_position:], min=0)
+            pos_emb = self.wpe(pos)
+            x = tok_emb + pos_emb
+        if self.embedding_fraction == 1:
+            x = self.emb_drop(x)
+        else:
+            x_shrunk = x * self.embedding_fraction + x.detach() * (1 - self.embedding_fraction)
+            assert isinstance(self.emb_drop, nn.Module)
+            x = self.emb_drop(x_shrunk)
+        (attn_bias, attention_mask) = self._attn_bias(device=x.device, dtype=x.dtype, attention_mask=attention_mask, prefix_mask=prefix_mask, sequence_id=sequence_id)
+        if use_cache and past_key_values is None:
+            past_key_values = [() for _ in range(self.config.n_layers)]
+        all_hidden_states = () if output_hidden_states else None
+        for (b_idx, block) in enumerate(self.blocks):
+            if output_hidden_states:
+                assert all_hidden_states is not None
+                all_hidden_states = all_hidden_states + (x,)
+            past_key_value = past_key_values[b_idx] if past_key_values is not None else None
+            (x, past_key_value) = block(x, past_key_value=past_key_value, attn_bias=attn_bias, attention_mask=attention_mask, is_causal=self.is_causal)
+            if past_key_values is not None:
+                past_key_values[b_idx] = past_key_value
+        x = self.norm_f(x)
+        return BaseModelOutputWithPast(last_hidden_state=x, past_key_values=past_key_values, hidden_states=all_hidden_states)
+
+    def param_init_fn(self, module):
+        init_fn_name = self.config.init_config['name']
+        MODEL_INIT_REGISTRY[init_fn_name](module=module, n_layers=self.config.n_layers, d_model=self.config.d_model, **self.config.init_config)
+
+    def fsdp_wrap_fn(self, module):
+        return isinstance(module, MPTBlock)
+
+    def activation_checkpointing_fn(self, module):
+        return isinstance(module, MPTBlock)
+
+class MPTForCausalLM(MPTPreTrainedModel):
+
+    def __init__(self, config: MPTConfig):
+        super().__init__(config)
+        if not config.tie_word_embeddings:
+            raise ValueError('MPTForCausalLM only supports tied word embeddings')
+        self.transformer = MPTModel(config)
+        self.logit_scale = None
+        if config.logit_scale is not None:
+            logit_scale = config.logit_scale
+            if isinstance(logit_scale, str):
+                if logit_scale == 'inv_sqrt_d_model':
+                    logit_scale = 1 / math.sqrt(config.d_model)
+                else:
+                    raise ValueError(f"logit_scale={logit_scale!r} is not recognized as an option; use numeric value or 'inv_sqrt_d_model'.")
+            self.logit_scale = logit_scale
+
+    def get_input_embeddings(self):
+        return self.transformer.wte
+
+    def set_input_embeddings(self, value):
+        self.transformer.wte = value
+
+    def get_output_embeddings(self):
+        return self.transformer.wte
+
+    def set_output_embeddings(self, new_embeddings):
+        self.transformer.wte = new_embeddings
+
+    def set_decoder(self, decoder):
+        self.transformer = decoder
+
+    def get_decoder(self):
+        return self.transformer
+
+    def forward(self, input_ids: torch.LongTensor, past_key_values: Optional[List[Tuple[torch.FloatTensor]]]=None, attention_mask: Optional[torch.ByteTensor]=None, prefix_mask: Optional[torch.ByteTensor]=None, sequence_id: Optional[torch.LongTensor]=None, labels: Optional[torch.LongTensor]=None, return_dict: Optional[bool]=None, output_attentions: Optional[bool]=None, output_hidden_states: Optional[bool]=None, use_cache: Optional[bool]=None):
+        return_dict = return_dict if return_dict is not None else self.config.return_dict
+        use_cache = use_cache if use_cache is not None else self.config.use_cache
+        outputs = self.transformer(input_ids=input_ids, past_key_values=past_key_values, attention_mask=attention_mask, prefix_mask=prefix_mask, sequence_id=sequence_id, return_dict=return_dict, output_attentions=output_attentions, output_hidden_states=output_hidden_states, use_cache=use_cache)
+        logits = F.linear(outputs.last_hidden_state, self.transformer.wte.weight)
+        if self.logit_scale is not None:
+            if self.logit_scale == 0:
+                warnings.warn(f'Multiplying logits by self.logit_scale={self.logit_scale!r}. This will produce uniform (uninformative) outputs.')
+            logits *= self.logit_scale
+        loss = None
+        if labels is not None:
+            labels = torch.roll(labels, shifts=-1)
+            labels[:, -1] = -100
+            loss = F.cross_entropy(logits.view(-1, logits.size(-1)), labels.to(logits.device).view(-1))
+        return CausalLMOutputWithPast(loss=loss, logits=logits, past_key_values=outputs.past_key_values, hidden_states=outputs.hidden_states)
+
+    def param_init_fn(self, module):
+        init_fn_name = self.config.init_config['name']
+        MODEL_INIT_REGISTRY[init_fn_name](module=module, n_layers=self.config.n_layers, d_model=self.config.d_model, **self.config.init_config)
+
+    def fsdp_wrap_fn(self, module):
+        return isinstance(module, MPTBlock)
+
+    def activation_checkpointing_fn(self, module):
+        return isinstance(module, MPTBlock)
+
+    def prepare_inputs_for_generation(self, input_ids, past_key_values=None, inputs_embeds=None, **kwargs):
+        if inputs_embeds is not None:
+            raise NotImplementedError('inputs_embeds is not implemented for MPT yet')
+        attention_mask = kwargs['attention_mask'].bool()
+        if attention_mask[:, -1].sum() != attention_mask.shape[0]:
+            raise NotImplementedError('MPT does not support generation with right padding.')
+        if self.transformer.attn_uses_sequence_id and self.training:
+            sequence_id = torch.zeros_like(input_ids[:1])
+        else:
+            sequence_id = None
+        if past_key_values is not None:
+            input_ids = input_ids[:, -1].unsqueeze(-1)
+        if self.transformer.prefix_lm:
+            prefix_mask = torch.ones_like(attention_mask)
+            if kwargs.get('use_cache') == False:
+                raise NotImplementedError('MPT with prefix_lm=True does not support use_cache=False.')
+        else:
+            prefix_mask = None
+        return {'input_ids': input_ids, 'attention_mask': attention_mask, 'prefix_mask': prefix_mask, 'sequence_id': sequence_id, 'past_key_values': past_key_values, 'use_cache': kwargs.get('use_cache', True)}
+
+    @staticmethod
+    def _reorder_cache(past_key_values, beam_idx):
+        """Used by HuggingFace generate when using beam search with kv-caching.
+
+        See https://github.com/huggingface/transformers/blob/3ec7a47664ebe40c40f4b722f6bb1cd30c3821ec/src/transformers/models/gpt2/modeling_gpt2.py#L1122-L1133
+        for an example in transformers.
+        """
+        reordered_past = []
+        for layer_past in past_key_values:
+            reordered_past += [tuple((past_state.index_select(0, beam_idx) for past_state in layer_past))]
+        return reordered_past

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_}