github/ColossalAI
1
0
Fork 0
mirror of https://github.com/hpcaitech/ColossalAI.git synced 2025-09-09 21:09:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

[legacy] clean up legacy code (#4743)

Browse Source 
* [legacy] remove outdated codes of pipeline (#4692)

* [legacy] remove cli of benchmark and update optim (#4690)

* [legacy] remove cli of benchmark and update optim

* [doc] fix cli doc test

* [legacy] fix engine clip grad norm

* [legacy] remove outdated colo tensor (#4694)

* [legacy] remove outdated colo tensor

* [test] fix test import

* [legacy] move outdated zero to legacy (#4696)

* [legacy] clean up utils (#4700)

* [legacy] clean up utils

* [example] update examples

* [legacy] clean up amp

* [legacy] fix amp module

* [legacy] clean up gpc (#4742)

* [legacy] clean up context

* [legacy] clean core, constants and global vars

* [legacy] refactor initialize

* [example] fix examples ci

* [example] fix examples ci

* [legacy] fix tests

* [example] fix gpt example

* [example] fix examples ci

* [devops] fix ci installation

* [example] fix examples ci
This commit is contained in:
Hongxin Liu
2023-09-18 16:31:06 +08:00
committed by GitHub
parent 32e7f99416
commit b5f9e37c70
342 changed files with 2919 additions and 4182 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
examples/tutorial/sequence_parallel/model/layers/head.py
View File

@@ -1,15 +1,17 @@
import colossalai
import torch
import torch.nn as nn
import torch.nn.functional as F
from .pooler import Pooler
from .linear import Linear
from .embedding import VocabEmbedding
from colossalai.core import global_context as gpc
from colossalai.context import ParallelMode
from colossalai.kernel import LayerNorm
from loss_func.cross_entropy import vocab_cross_entropy
import colossalai
from colossalai.kernel import LayerNorm
from colossalai.legacy.context import ParallelMode
from colossalai.legacy.core import global_context as gpc
from .embedding import VocabEmbedding
from .linear import Linear
from .pooler import Pooler
class BertLMHead(nn.Module):
"""Masked LM head for Bert
@@ -19,10 +21,11 @@ class BertLMHead(nn.Module):
layernorm_epsilon: tolerance for layer norm divisions
"""
def __init__(self,
vocab_size,
hidden_size,
):
def __init__(
self,
vocab_size,
hidden_size,
):
super(BertLMHead, self).__init__()
self.bias = torch.nn.Parameter(torch.zeros(vocab_size))

9
examples/tutorial/sequence_parallel/model/layers/preprocess.py
View File

@@ -1,7 +1,8 @@
from colossalai.context.parallel_mode import ParallelMode
import torch
import torch.nn as nn
from colossalai.core import global_context as gpc
from colossalai.legacy.context.parallel_mode import ParallelMode
from colossalai.legacy.core import global_context as gpc
class PreProcessor(nn.Module):
@@ -14,8 +15,8 @@ class PreProcessor(nn.Module):
# Create position ids
seq_length = token_ids.size(1)
local_rank = gpc.get_local_rank(ParallelMode.SEQUENCE)
position_ids = torch.arange(seq_length*local_rank,
seq_length * (local_rank+1),
position_ids = torch.arange(seq_length * local_rank,
seq_length * (local_rank + 1),
dtype=torch.long,
device=token_ids.device)
position_ids = position_ids.unsqueeze(0).expand_as(token_ids)