René's URL Explorer Experiment

Title: GitHub - deepspeedai/Megatron-DeepSpeed: Ongoing research training transformer language models at scale, including: BERT & GPT-2 · GitHub

Open Graph Title: GitHub - deepspeedai/Megatron-DeepSpeed: Ongoing research training transformer language models at scale, including: BERT & GPT-2

X Title: GitHub - deepspeedai/Megatron-DeepSpeed: Ongoing research training transformer language models at scale, including: BERT & GPT-2

Description: Ongoing research training transformer language models at scale, including: BERT & GPT-2 - deepspeedai/Megatron-DeepSpeed

Open Graph Description: Ongoing research training transformer language models at scale, including: BERT & GPT-2 - deepspeedai/Megatron-DeepSpeed

X Description: Ongoing research training transformer language models at scale, including: BERT & GPT-2 - deepspeedai/Megatron-DeepSpeed

Opengraph URL: https://github.com/deepspeedai/Megatron-DeepSpeed

X: @github

direct link

Domain: github.com

route-pattern	/:user_id/:repository
route-controller	files
route-action	disambiguate
fetch-nonce	v2:7d90f5cc-8530-e887-bad4-606e22bd7e92
current-catalog-service-hash	f3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-id	C0D4:19F979:C372B7:10C2506:6A4C9470
html-safe-nonce	a407a3767b753b7edc9c1a863b310c5b554cf4344da9ef14b2aecc7f9bc605cf
visitor-payload	eyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJDMEQ0OjE5Rjk3OTpDMzcyQjc6MTBDMjUwNjo2QTRDOTQ3MCIsInZpc2l0b3JfaWQiOiIzMjUwNTY3NTgyMjQ4MTEzMjY0IiwicmVnaW9uX2VkZ2UiOiJpYWQiLCJyZWdpb25fcmVuZGVyIjoiaWFkIn0=
visitor-hmac	f8589bf04e2384738af465bc16e5482ce2fd66743c11e72c3d376fd220aab657
hovercard-subject-tag	repository:379078148
github-keyboard-shortcuts	repository,copilot
google-site-verification	Apib7-x98H0j5cPqHWwSMm6dNU4GmODRoqxLiDzdx9I
octolytics-url	https://collector.github.com/github/collect
analytics-location	//
fb:app_id	1401488693436528
apple-itunes-app	app-id=1477376905, app-argument=https://github.com/deepspeedai/Megatron-DeepSpeed
twitter:image	https://opengraph.githubassets.com/0ab3d9c2f3740ba4c211b536e8765e4bd568f6ca26942387ba8d8036d2d62248/deepspeedai/Megatron-DeepSpeed
twitter:card	summary_large_image
og:image	https://opengraph.githubassets.com/0ab3d9c2f3740ba4c211b536e8765e4bd568f6ca26942387ba8d8036d2d62248/deepspeedai/Megatron-DeepSpeed
og:image:alt	Ongoing research training transformer language models at scale, including: BERT & GPT-2 - deepspeedai/Megatron-DeepSpeed
og:image:width	1200
og:image:height	600
og:site_name	GitHub
og:type	object
hostname	github.com
expected-hostname	github.com
None	3d11bb817438277de2a940854450e83a7d32b6aeb5014e9e6b00a6423900251c
turbo-cache-control	no-cache
go-import	github.com/deepspeedai/Megatron-DeepSpeed git https://github.com/deepspeedai/Megatron-DeepSpeed.git
octolytics-dimension-user_id	74068820
octolytics-dimension-user_login	deepspeedai
octolytics-dimension-repository_id	379078148
octolytics-dimension-repository_nwo	deepspeedai/Megatron-DeepSpeed
octolytics-dimension-repository_public	true
octolytics-dimension-repository_is_fork	true
octolytics-dimension-repository_parent_id	176982014
octolytics-dimension-repository_parent_nwo	NVIDIA/Megatron-LM
octolytics-dimension-repository_network_root_id	176982014
octolytics-dimension-repository_network_root_nwo	NVIDIA/Megatron-LM
turbo-body-classes	logged-out env-production page-responsive
disable-turbo	false
browser-stats-url	https://api.github.com/_private/browser/stats
browser-errors-url	https://api.github.com/_private/browser/errors
release	7a2dede45637df6b92ddcfe2a557e67d4b5854ae
ui-target	full
theme-color	#1e2327
color-scheme	light dark

Links:

Skip to content	https://github.com/microsoft/Megatron-DeepSpeed#start-of-content
	https://github.com/
Sign in	https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fdeepspeedai%2FMegatron-DeepSpeed
GitHub CopilotWrite better code with AI	https://github.com/features/copilot
GitHub Copilot appDirect agents from issue to merge	https://github.com/features/ai/github-app
MCP RegistryNewIntegrate external tools	https://github.com/mcp
ActionsAutomate any workflow	https://github.com/features/actions
CodespacesInstant dev environments	https://github.com/features/codespaces
IssuesPlan and track work	https://github.com/features/issues
Code ReviewManage code changes	https://github.com/features/code-review
GitHub Advanced SecurityFind and fix vulnerabilities	https://github.com/security/advanced-security
Code securitySecure your code as you build	https://github.com/security/advanced-security/code-security
Secret protectionStop leaks before they start	https://github.com/security/advanced-security/secret-protection
Why GitHub	https://github.com/why-github
Documentation	https://docs.github.com
Blog	https://github.blog
Changelog	https://github.blog/changelog
Marketplace	https://github.com/marketplace
View all features	https://github.com/features
Enterprises	https://github.com/enterprise
Small and medium teams	https://github.com/team
Startups	https://github.com/enterprise/startups
Nonprofits	https://github.com/solutions/industry/nonprofits
App Modernization	https://github.com/solutions/use-case/app-modernization
DevSecOps	https://github.com/solutions/use-case/devsecops
DevOps	https://github.com/solutions/use-case/devops
CI/CD	https://github.com/solutions/use-case/ci-cd
View all use cases	https://github.com/solutions/use-case
Healthcare	https://github.com/solutions/industry/healthcare
Financial services	https://github.com/solutions/industry/financial-services
Manufacturing	https://github.com/solutions/industry/manufacturing
Government	https://github.com/solutions/industry/government
View all industries	https://github.com/solutions/industry
View all solutions	https://github.com/solutions
AI	https://github.com/resources/articles?topic=ai
Software Development	https://github.com/resources/articles?topic=software-development
DevOps	https://github.com/resources/articles?topic=devops
Security	https://github.com/resources/articles?topic=security
View all topics	https://github.com/resources/articles
Customer stories	https://github.com/customer-stories
Events & webinars	https://github.com/resources/events
Ebooks & reports	https://github.com/resources/whitepapers
Business insights	https://github.com/solutions/executive-insights
GitHub Skills	https://skills.github.com
Documentation	https://docs.github.com
Customer support	https://support.github.com
Community forum	https://github.com/orgs/community/discussions
Trust center	https://github.com/trust-center
Partners	https://github.com/partners
View all resources	https://github.com/resources
GitHub SponsorsFund open source developers	https://github.com/sponsors
Security Lab	https://securitylab.github.com
Maintainer Community	https://maintainers.github.com
Accelerator	https://github.com/accelerator
GitHub Stars	https://stars.github.com
Archive Program	https://archiveprogram.github.com
Topics	https://github.com/topics
Trending	https://github.com/trending
Collections	https://github.com/collections
Enterprise platformAI-powered developer platform	https://github.com/enterprise
GitHub Advanced SecurityEnterprise-grade security features	https://github.com/security/advanced-security
Copilot for BusinessEnterprise-grade AI features	https://github.com/features/copilot/copilot-business
Premium SupportEnterprise-grade 24/7 support	https://github.com/premium-support
Pricing	https://github.com/pricing
Search syntax tips	https://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
documentation	https://docs.github.com/search-github/github-code-search/understanding-github-code-search-syntax
Sign in	https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fdeepspeedai%2FMegatron-DeepSpeed
Sign up	https://github.com/signup?ref_cta=Sign+up&ref_loc=header+logged+out&ref_page=%2F%3Cuser-name%3E%2F%3Crepo-name%3E&source=header-repo&source_repo=deepspeedai%2FMegatron-DeepSpeed
Reload	https://github.com/microsoft/Megatron-DeepSpeed
Reload	https://github.com/microsoft/Megatron-DeepSpeed
Reload	https://github.com/microsoft/Megatron-DeepSpeed
Please reload this page	https://github.com/microsoft/Megatron-DeepSpeed
deepspeedai	https://github.com/deepspeedai
Megatron-DeepSpeed	https://github.com/deepspeedai/Megatron-DeepSpeed
NVIDIA/Megatron-LM	https://github.com/NVIDIA/Megatron-LM
Notifications	https://github.com/login?return_to=%2Fdeepspeedai%2FMegatron-DeepSpeed
Fork 368	https://github.com/login?return_to=%2Fdeepspeedai%2FMegatron-DeepSpeed
Star 2.3k	https://github.com/login?return_to=%2Fdeepspeedai%2FMegatron-DeepSpeed
Code	https://github.com/deepspeedai/Megatron-DeepSpeed
Issues 139	https://github.com/deepspeedai/Megatron-DeepSpeed/issues
Pull requests 22	https://github.com/deepspeedai/Megatron-DeepSpeed/pulls
Actions	https://github.com/deepspeedai/Megatron-DeepSpeed/actions
Projects	https://github.com/deepspeedai/Megatron-DeepSpeed/projects
Security and quality 0	https://github.com/deepspeedai/Megatron-DeepSpeed/security
Insights	https://github.com/deepspeedai/Megatron-DeepSpeed/pulse
Code	https://github.com/deepspeedai/Megatron-DeepSpeed
Issues	https://github.com/deepspeedai/Megatron-DeepSpeed/issues
Pull requests	https://github.com/deepspeedai/Megatron-DeepSpeed/pulls
Actions	https://github.com/deepspeedai/Megatron-DeepSpeed/actions
Projects	https://github.com/deepspeedai/Megatron-DeepSpeed/projects
Security and quality	https://github.com/deepspeedai/Megatron-DeepSpeed/security
Insights	https://github.com/deepspeedai/Megatron-DeepSpeed/pulse
	https://github.com/deepspeedai/Megatron-DeepSpeed
Branches	https://github.com/deepspeedai/Megatron-DeepSpeed/branches
Tags	https://github.com/deepspeedai/Megatron-DeepSpeed/tags
	https://github.com/deepspeedai/Megatron-DeepSpeed/branches
	https://github.com/deepspeedai/Megatron-DeepSpeed/tags
2,252 Commits	https://github.com/deepspeedai/Megatron-DeepSpeed/commits/main/
	https://github.com/deepspeedai/Megatron-DeepSpeed/commits/main/
.github/workflows	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/.github/workflows
.github/workflows	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/.github/workflows
dataset	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/dataset
dataset	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/dataset
docs	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/docs
docs	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/docs
examples	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/examples
examples	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/examples
examples_deepspeed	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/examples_deepspeed
examples_deepspeed	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/examples_deepspeed
images	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/images
images	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/images
megatron	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/megatron
megatron	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/megatron
tasks	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/tasks
tasks	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/tasks
tests	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/tests
tests	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/tests
tools	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/tools
tools	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/tools
.coveragerc	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/.coveragerc
.coveragerc	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/.coveragerc
.gitignore	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/.gitignore
.gitignore	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/.gitignore
.gitlab-ci.yml	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/.gitlab-ci.yml
.gitlab-ci.yml	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/.gitlab-ci.yml
CODEOWNERS	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/CODEOWNERS
CODEOWNERS	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/CODEOWNERS
LICENSE	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/LICENSE
LICENSE	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/LICENSE
MANIFEST.in	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/MANIFEST.in
MANIFEST.in	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/MANIFEST.in
README.md	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/README.md
README.md	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/README.md
SECURITY.md	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/SECURITY.md
SECURITY.md	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/SECURITY.md
finetune_llama.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/finetune_llama.py
finetune_llama.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/finetune_llama.py
pretrain_bert.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_bert.py
pretrain_bert.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_bert.py
pretrain_gpt.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_gpt.py
pretrain_gpt.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_gpt.py
pretrain_gpt_core.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_gpt_core.py
pretrain_gpt_core.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_gpt_core.py
pretrain_ict.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_ict.py
pretrain_ict.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_ict.py
pretrain_retro.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_retro.py
pretrain_retro.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_retro.py
pretrain_t5.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_t5.py
pretrain_t5.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_t5.py
pretrain_vision_classify.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_vision_classify.py
pretrain_vision_classify.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_vision_classify.py
pretrain_vision_dino.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_vision_dino.py
pretrain_vision_dino.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_vision_dino.py
pretrain_vision_inpaint.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_vision_inpaint.py
pretrain_vision_inpaint.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/pretrain_vision_inpaint.py
setup.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/setup.py
setup.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/setup.py
README	https://github.com/microsoft/Megatron-DeepSpeed
License	https://github.com/microsoft/Megatron-DeepSpeed
Security	https://github.com/microsoft/Megatron-DeepSpeed
	https://github.com/microsoft/Megatron-DeepSpeed#latest-news
upstream	https://github.com/NVIDIA/Megatron-LM
rebase folder for more details	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/main/examples_deepspeed/rebase
	https://github.com/microsoft/Megatron-DeepSpeed#megatron-deepspeed
	https://github.com/microsoft/Megatron-DeepSpeed#recent-sync-with-nvidiamegatron-lm
backup branch	https://github.com/deepspeedai/Megatron-DeepSpeed/tree/before_rebase
	https://github.com/microsoft/Megatron-DeepSpeed#run-on-azure-and-azureml
	https://github.com/microsoft/Megatron-DeepSpeed#below-is-megatron-lms-original-readme-note-that-examples-mentioned-below-are-from-the-original-nvidiamegatron-lm-repo-all-of-them-do-not-have-deepspeed-technologies-integrations-and-some-of-them-may-not-work-due-to-changes-in-this-megatron-deepspeed-repo-thus-we-recommend-you-to-go-to-examples_deepspeed-folder-which-includes-examples-that-have-deepspeed-technologies-integrated-and-are-tested-by-deepspeed-team
1	https://arxiv.org/pdf/1909.08053.pdf
2	https://arxiv.org/pdf/2104.04473.pdf
3	https://arxiv.org/pdf/2205.05198
tensor	https://arxiv.org/pdf/1909.08053.pdf
sequence	https://arxiv.org/pdf/2205.05198
pipeline	https://arxiv.org/pdf/2104.04473.pdf
GPT	https://arxiv.org/abs/2005.14165
BERT	https://arxiv.org/pdf/1810.04805.pdf
T5	https://arxiv.org/abs/1910.10683
BERT and GPT Studies Using Megatron	https://arxiv.org/pdf/1909.08053.pdf
BioMegatron: Larger Biomedical Domain Language Model	https://www.aclweb.org/anthology/2020.emnlp-main.379.pdf
End-to-End Training of Neural Retrievers for Open-Domain Question Answering	https://arxiv.org/abs/2101.00408
Large Scale Multi-Actor Generative Dialog Modeling	https://www.aclweb.org/anthology/2020.acl-main.8.pdf
Local Knowledge Powered Conversational Agents	https://arxiv.org/abs/2010.10150
MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models	https://www.aclweb.org/anthology/2020.emnlp-main.226.pdf
RACE Reading Comprehension Dataset Leaderboard	http://www.qizhexie.com/data/RACE_leaderboard.html
Training Question Answering Models From Synthetic Data	https://www.aclweb.org/anthology/2020.emnlp-main.468.pdf
Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases	https://arxiv.org/abs/2112.07868
Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models	https://arxiv.org/abs/2202.04173
Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model	https://arxiv.org/abs/2201.11990
Multi-Stage Prompting for Knowledgeable Dialogue Generation	https://arxiv.org/abs/2203.08745
NeMo Megatron	https://developer.nvidia.com/nvidia-nemo#nemo-megatron
NVIDIA's Selene supercomputer	https://www.top500.org/system/179842/
A100	https://www.nvidia.com/en-us/data-center/a100/
	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/images/Achieved_petaFLOPs.png
our paper	https://arxiv.org/pdf/2205.05198
	https://github.com/microsoft/Megatron-DeepSpeed#contents
Contents	https://github.com/microsoft/Megatron-DeepSpeed#contents
Setup	https://github.com/microsoft/Megatron-DeepSpeed#setup
Downloading Checkpoints	https://github.com/microsoft/Megatron-DeepSpeed#downloading-checkpoints
Usage	https://github.com/microsoft/Megatron-DeepSpeed#usage
Training	https://github.com/microsoft/Megatron-DeepSpeed#training
Data Preprocessing	https://github.com/microsoft/Megatron-DeepSpeed#data-preprocessing
BERT Pretraining	https://github.com/microsoft/Megatron-DeepSpeed#bert-pretraining
GPT Pretraining	https://github.com/microsoft/Megatron-DeepSpeed#gpt-pretraining
T5 Pretraining	https://github.com/microsoft/Megatron-DeepSpeed#t5-pretraining
Distributed Pretraining	https://github.com/microsoft/Megatron-DeepSpeed#distributed-pretraining
Activation Checkpointing and Recomputation	https://github.com/microsoft/Megatron-DeepSpeed#activation-checkpointing-and-recomputation
Distributed Optimizer	https://github.com/microsoft/Megatron-DeepSpeed#distributed-optimizer
FlashAttention	https://github.com/microsoft/Megatron-DeepSpeed#flashattention
GPT-3 Example	https://github.com/microsoft/Megatron-DeepSpeed#gpt-3-example
Retro	https://github.com/microsoft/Megatron-DeepSpeed#retro
Evaluation and Tasks	https://github.com/microsoft/Megatron-DeepSpeed#evaluation-and-tasks
GPT Text Generation	https://github.com/microsoft/Megatron-DeepSpeed#gpt-text-generation
GPT Evaluation	https://github.com/microsoft/Megatron-DeepSpeed#gpt-evaluation
WikiText Perplexity Evaluation	https://github.com/microsoft/Megatron-DeepSpeed#wikitext-perplexity-evaluation
LAMBADA Cloze Accuracy	https://github.com/microsoft/Megatron-DeepSpeed#lambada-cloze-accuracy
BERT Task Evaluation	https://github.com/microsoft/Megatron-DeepSpeed#bert-task-evaluation
RACE Evaluation	https://github.com/microsoft/Megatron-DeepSpeed#race-evaluation
MNLI Evaluation	https://github.com/microsoft/Megatron-DeepSpeed#mnli-evaluation
Datasets	https://github.com/microsoft/Megatron-DeepSpeed#datasets
Collecting Wikipedia Training Data	https://github.com/microsoft/Megatron-DeepSpeed#collecting-wikipedia-training-data
Collecting GPT Webtext Data	https://github.com/microsoft/Megatron-DeepSpeed#collecting-gpt-webtext-data
Reproducibility	https://github.com/microsoft/Megatron-DeepSpeed#reproducibility
	https://github.com/microsoft/Megatron-DeepSpeed#setup
NGC's PyTorch container	https://ngc.nvidia.com/catalog/containers/nvidia:pytorch
APEX	https://github.com/NVIDIA/apex#quick-start
NLTK	https://www.nltk.org/install.html
	https://github.com/microsoft/Megatron-DeepSpeed#downloading-checkpoints
BERT-345M	https://ngc.nvidia.com/catalog/models/nvidia:megatron_bert_345m
GPT-345M	https://ngc.nvidia.com/catalog/models/nvidia:megatron_lm_345m
sign up	https://ngc.nvidia.com/signup
setup	https://ngc.nvidia.com/setup/installers/cli
NGC documentation	https://docs.nvidia.com/dgx/ngc-registry-cli-user-guide/index.html#topic_6_4_1
uncased	https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-uncased-vocab.txt
cased	https://s3.amazonaws.com/models.huggingface.co/bert/bert-large-cased-vocab.txt
vocab file	https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-vocab.json
merge table	https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-merges.txt
	https://github.com/microsoft/Megatron-DeepSpeed#usage
examples	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/examples
	https://github.com/microsoft/Megatron-DeepSpeed#training
	https://github.com/microsoft/Megatron-DeepSpeed#data-preprocessing
preprocess_data.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/tools/preprocess_data.py
preprocess_data.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/tools/preprocess_data.py
	https://github.com/microsoft/Megatron-DeepSpeed#bert-pretraining
examples/pretrain_bert.sh	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/examples/pretrain_bert.sh
arguments.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/megatron/arguments.py
Setup	https://github.com/microsoft/Megatron-DeepSpeed#setup
	https://github.com/microsoft/Megatron-DeepSpeed#gpt-pretraining
arguments.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/megatron/arguments.py
	https://github.com/microsoft/Megatron-DeepSpeed#t5-pretraining
	https://github.com/microsoft/Megatron-DeepSpeed#distributed-pretraining
documentation	https://pytorch.org/docs/stable/elastic/run.html#launcher-api
environment variables	https://pytorch.org/docs/stable/distributed.html#environment-variable-initialization
nccl	https://developer.nvidia.com/nccl
our paper	https://arxiv.org/pdf/1909.08053.pdf
our paper	https://arxiv.org/pdf/2205.05198.pdf
our paper	https://arxiv.org/pdf/2104.04473.pdf
our paper	https://arxiv.org/pdf/2104.04473.pdf
	https://github.com/microsoft/Megatron-DeepSpeed#activation-checkpointing-and-recomputation
our paper	https://arxiv.org/pdf/2205.05198
	https://github.com/microsoft/Megatron-DeepSpeed#distributed-optimizer
ZeRO: Memory Optimizations Toward Training Trillion Parameter Models	https://arxiv.org/abs/1910.02054
	https://github.com/microsoft/Megatron-DeepSpeed#flashattention
FlashAttention	https://github.com/HazyResearch/flash-attention
	https://github.com/microsoft/Megatron-DeepSpeed#gpt-3-example
GPT-3	https://arxiv.org/abs/2005.14165
slurm	https://slurm.schedmd.com/documentation.html
pyxis	https://github.com/NVIDIA/pyxis
	https://github.com/microsoft/Megatron-DeepSpeed#retro
Improving language models by retrieving from trillions of tokens	https://arxiv.org/abs/2112.04426
	https://github.com/microsoft/Megatron-DeepSpeed#evaluation-and-tasks
	https://github.com/microsoft/Megatron-DeepSpeed#gpt-text-generation
examples/run_text_generation_server_345M.sh	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/examples/run_text_generation_server_345M.sh
megatron/text_generation_server.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/megatron/text_generation_server.py
	https://github.com/microsoft/Megatron-DeepSpeed#detoxify-gpt-via-self-generation
examples/detxoify_lm/README.md	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/examples/detxoify_lm/README.md
	https://github.com/microsoft/Megatron-DeepSpeed#gpt-evaluation
	https://github.com/microsoft/Megatron-DeepSpeed#wikitext-perplexity-evaluation
WikiText-103 test dataset	https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-103-v1.zip
	https://github.com/microsoft/Megatron-DeepSpeed#lambada-cloze-accuracy
LAMBADA dataset	https://github.com/cybertronai/bflm/blob/master/lambada_test.jsonl
WikiText Perplexity Evaluation	https://github.com/microsoft/Megatron-DeepSpeed#wikitext-perplexity-evaluation
main.py	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/tasks/main.py
	https://github.com/microsoft/Megatron-DeepSpeed#bert-task-evaluation
	https://github.com/microsoft/Megatron-DeepSpeed#race-evaluation
RACE dataset	http://www.cs.cmu.edu/~glai1/data/race/
	https://github.com/microsoft/Megatron-DeepSpeed#mnli-evaluation
MultiNLI sentence pair corpus	https://www.nyu.edu/projects/bowman/multinli/
Quora Question Pairs	https://www.kaggle.com/quora/question-pairs-dataset
RACE Evaluation	https://github.com/microsoft/Megatron-DeepSpeed#race-evaluation
RACE Evaluation	https://github.com/microsoft/Megatron-DeepSpeed#race-evaluation
	https://github.com/microsoft/Megatron-DeepSpeed#datasets
	https://github.com/microsoft/Megatron-DeepSpeed#collecting-wikipedia-training-data
the latest dump	https://dumps.wikimedia.org/enwiki/latest/enwiki-latest-pages-articles.xml.bz2
WikiExtractor.py	https://github.com/attardi/wikiextractor
above	https://github.com/microsoft/Megatron-DeepSpeed#data-preprocessing
	https://github.com/microsoft/Megatron-DeepSpeed#collecting-gpt-webtext-data
OpenWebText	https://github.com/eukaryote31/openwebtext
jcpeterson	https://github.com/jcpeterson/openwebtext
eukaryote31's	https://github.com/eukaryote31/openwebtext
openwebtext	https://github.com/deepspeedai/Megatron-DeepSpeed/blob/main/tools/openwebtext
	https://github.com/microsoft/Megatron-DeepSpeed#reproducibility
Readme	https://github.com/microsoft/Megatron-DeepSpeed#readme-ov-file
View license	https://github.com/microsoft/Megatron-DeepSpeed#License-1-ov-file
Security policy	https://github.com/microsoft/Megatron-DeepSpeed#security-ov-file
Please reload this page	https://github.com/microsoft/Megatron-DeepSpeed
Activity	https://github.com/deepspeedai/Megatron-DeepSpeed/activity
Custom properties	https://github.com/deepspeedai/Megatron-DeepSpeed/custom-properties
368 forks	https://github.com/deepspeedai/Megatron-DeepSpeed/forks
Report repository	https://github.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2Fdeepspeedai%2FMegatron-DeepSpeed&report=deepspeedai+%28user%29
Releases	https://github.com/deepspeedai/Megatron-DeepSpeed/releases
9 tags	https://github.com/deepspeedai/Megatron-DeepSpeed/tags
Packages 0	https://github.com/orgs/deepspeedai/packages?repo_name=Megatron-DeepSpeed
Please reload this page	https://github.com/microsoft/Megatron-DeepSpeed
Please reload this page	https://github.com/microsoft/Megatron-DeepSpeed
Contributors	https://github.com/deepspeedai/Megatron-DeepSpeed/graphs/contributors
Please reload this page	https://github.com/microsoft/Megatron-DeepSpeed
	https://github.com
Terms	https://docs.github.com/site-policy/github-terms/github-terms-of-service
Privacy	https://docs.github.com/site-policy/privacy-policies/github-privacy-statement
Security	https://github.com/security
Status	https://www.githubstatus.com/
Community	https://github.community/
Docs	https://docs.github.com/
Contact	https://support.github.com?tags=dotcom-footer

Viewport: width=device-width

URLs of crawlers that visited me.