René's URL Explorer Experiment

Title: GitHub - microsoft/ArchScale: Simple & Scalable Pretraining for Neural Architecture Research · GitHub

Open Graph Title: GitHub - microsoft/ArchScale: Simple & Scalable Pretraining for Neural Architecture Research

X Title: GitHub - microsoft/ArchScale: Simple & Scalable Pretraining for Neural Architecture Research

Description: Simple & Scalable Pretraining for Neural Architecture Research - microsoft/ArchScale

Open Graph Description: Simple & Scalable Pretraining for Neural Architecture Research - microsoft/ArchScale

X Description: Simple & Scalable Pretraining for Neural Architecture Research - microsoft/ArchScale

Opengraph URL: https://github.com/microsoft/ArchScale

X: @github

direct link

Domain: github.com

route-pattern	/:user_id/:repository
route-controller	files
route-action	disambiguate
fetch-nonce	v2:3e6d0de5-b4f6-8c73-d881-c81fcde4c38d
current-catalog-service-hash	f3abb0cc802f3d7b95fc8762b94bdcb13bf39634c40c357301c4aa1d67a256fb
request-id	AEDC:174B86:4FBA3C:6B5723:6A4D3CFD
html-safe-nonce	6ca096cbf46ec7cfa7c4ca1436777a3cfe9d077a60264760ab8e8ca5fa99bcc0
visitor-payload	eyJyZWZlcnJlciI6IiIsInJlcXVlc3RfaWQiOiJBRURDOjE3NEI4Njo0RkJBM0M6NkI1NzIzOjZBNEQzQ0ZEIiwidmlzaXRvcl9pZCI6IjY2MTExMzUzMzk2NTcyNDc5OTciLCJyZWdpb25fZWRnZSI6ImlhZCIsInJlZ2lvbl9yZW5kZXIiOiJpYWQifQ==
visitor-hmac	08bfe71f7882aa0e083d4650cf8378378d0a0265d101dfc8c46864d69273a85f
hovercard-subject-tag	repository:1009405275
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/microsoft/ArchScale
twitter:image	https://opengraph.githubassets.com/a8d738c8c29059a4004bca8cc1e29702b3a899fe7f846684de52960ff6f6fbc7/microsoft/ArchScale
twitter:card	summary_large_image
og:image	https://opengraph.githubassets.com/a8d738c8c29059a4004bca8cc1e29702b3a899fe7f846684de52960ff6f6fbc7/microsoft/ArchScale
og:image:alt	Simple & Scalable Pretraining for Neural Architecture Research - microsoft/ArchScale
og:image:width	1200
og:image:height	600
og:site_name	GitHub
og:type	object
hostname	github.com
expected-hostname	github.com
None	92571a8944142227b7e19cd10918b1ddd06e5066c1ad5bc7e4769cf6140a87e6
turbo-cache-control	no-cache
go-import	github.com/microsoft/ArchScale git https://github.com/microsoft/ArchScale.git
octolytics-dimension-user_id	6154722
octolytics-dimension-user_login	microsoft
octolytics-dimension-repository_id	1009405275
octolytics-dimension-repository_nwo	microsoft/ArchScale
octolytics-dimension-repository_public	true
octolytics-dimension-repository_is_fork	false
octolytics-dimension-repository_network_root_id	1009405275
octolytics-dimension-repository_network_root_nwo	microsoft/ArchScale
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	56fc8347865a14e2ec811533d68f929cf4e0ec19
ui-target	full
theme-color	#1e2327
color-scheme	light dark

Links:

Skip to content	https://github.com/microsoft/ArchScale#start-of-content
	https://github.com/
Sign in	https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fmicrosoft%2FArchScale
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%2Fmicrosoft%2FArchScale
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=microsoft%2FArchScale
Reload	https://github.com/microsoft/ArchScale
Reload	https://github.com/microsoft/ArchScale
Reload	https://github.com/microsoft/ArchScale
Please reload this page	https://github.com/microsoft/ArchScale
microsoft	https://github.com/microsoft
ArchScale	https://github.com/microsoft/ArchScale
Notifications	https://github.com/login?return_to=%2Fmicrosoft%2FArchScale
Fork 34	https://github.com/login?return_to=%2Fmicrosoft%2FArchScale
Star 334	https://github.com/login?return_to=%2Fmicrosoft%2FArchScale
Code	https://github.com/microsoft/ArchScale
Issues 0	https://github.com/microsoft/ArchScale/issues
Pull requests 0	https://github.com/microsoft/ArchScale/pulls
Actions	https://github.com/microsoft/ArchScale/actions
Projects	https://github.com/microsoft/ArchScale/projects
Models	https://github.com/microsoft/ArchScale/models
Security and quality 0	https://github.com/microsoft/ArchScale/security
Insights	https://github.com/microsoft/ArchScale/pulse
Code	https://github.com/microsoft/ArchScale
Issues	https://github.com/microsoft/ArchScale/issues
Pull requests	https://github.com/microsoft/ArchScale/pulls
Actions	https://github.com/microsoft/ArchScale/actions
Projects	https://github.com/microsoft/ArchScale/projects
Models	https://github.com/microsoft/ArchScale/models
Security and quality	https://github.com/microsoft/ArchScale/security
Insights	https://github.com/microsoft/ArchScale/pulse
	https://github.com/microsoft/ArchScale
Branches	https://github.com/microsoft/ArchScale/branches
Tags	https://github.com/microsoft/ArchScale/tags
	https://github.com/microsoft/ArchScale/branches
	https://github.com/microsoft/ArchScale/tags
48 Commits	https://github.com/microsoft/ArchScale/commits/main/
	https://github.com/microsoft/ArchScale/commits/main/
assets	https://github.com/microsoft/ArchScale/tree/main/assets
assets	https://github.com/microsoft/ArchScale/tree/main/assets
emerging_optimizers	https://github.com/microsoft/ArchScale/tree/main/emerging_optimizers
emerging_optimizers	https://github.com/microsoft/ArchScale/tree/main/emerging_optimizers
eval_reason	https://github.com/microsoft/ArchScale/tree/main/eval_reason
eval_reason	https://github.com/microsoft/ArchScale/tree/main/eval_reason
launch_scripts	https://github.com/microsoft/ArchScale/tree/main/launch_scripts
launch_scripts	https://github.com/microsoft/ArchScale/tree/main/launch_scripts
lit_gpt	https://github.com/microsoft/ArchScale/tree/main/lit_gpt
lit_gpt	https://github.com/microsoft/ArchScale/tree/main/lit_gpt
plots	https://github.com/microsoft/ArchScale/tree/main/plots
plots	https://github.com/microsoft/ArchScale/tree/main/plots
scripts	https://github.com/microsoft/ArchScale/tree/main/scripts
scripts	https://github.com/microsoft/ArchScale/tree/main/scripts
shuffle	https://github.com/microsoft/ArchScale/tree/main/shuffle
shuffle	https://github.com/microsoft/ArchScale/tree/main/shuffle
tests	https://github.com/microsoft/ArchScale/tree/main/tests
tests	https://github.com/microsoft/ArchScale/tree/main/tests
.amltignore	https://github.com/microsoft/ArchScale/blob/main/.amltignore
.amltignore	https://github.com/microsoft/ArchScale/blob/main/.amltignore
.gitignore	https://github.com/microsoft/ArchScale/blob/main/.gitignore
.gitignore	https://github.com/microsoft/ArchScale/blob/main/.gitignore
CONTRIBUTING.md	https://github.com/microsoft/ArchScale/blob/main/CONTRIBUTING.md
CONTRIBUTING.md	https://github.com/microsoft/ArchScale/blob/main/CONTRIBUTING.md
Dockerfile	https://github.com/microsoft/ArchScale/blob/main/Dockerfile
Dockerfile	https://github.com/microsoft/ArchScale/blob/main/Dockerfile
LICENSE	https://github.com/microsoft/ArchScale/blob/main/LICENSE
LICENSE	https://github.com/microsoft/ArchScale/blob/main/LICENSE
README.md	https://github.com/microsoft/ArchScale/blob/main/README.md
README.md	https://github.com/microsoft/ArchScale/blob/main/README.md
SECURITY.md	https://github.com/microsoft/ArchScale/blob/main/SECURITY.md
SECURITY.md	https://github.com/microsoft/ArchScale/blob/main/SECURITY.md
eval.py	https://github.com/microsoft/ArchScale/blob/main/eval.py
eval.py	https://github.com/microsoft/ArchScale/blob/main/eval.py
eval_phonebook.py	https://github.com/microsoft/ArchScale/blob/main/eval_phonebook.py
eval_phonebook.py	https://github.com/microsoft/ArchScale/blob/main/eval_phonebook.py
eval_proofpile.py	https://github.com/microsoft/ArchScale/blob/main/eval_proofpile.py
eval_proofpile.py	https://github.com/microsoft/ArchScale/blob/main/eval_proofpile.py
install.sh	https://github.com/microsoft/ArchScale/blob/main/install.sh
install.sh	https://github.com/microsoft/ArchScale/blob/main/install.sh
logging_utils.py	https://github.com/microsoft/ArchScale/blob/main/logging_utils.py
logging_utils.py	https://github.com/microsoft/ArchScale/blob/main/logging_utils.py
plot_data_scaling.py	https://github.com/microsoft/ArchScale/blob/main/plot_data_scaling.py
plot_data_scaling.py	https://github.com/microsoft/ArchScale/blob/main/plot_data_scaling.py
plot_flops_scaling.py	https://github.com/microsoft/ArchScale/blob/main/plot_flops_scaling.py
plot_flops_scaling.py	https://github.com/microsoft/ArchScale/blob/main/plot_flops_scaling.py
precision.py	https://github.com/microsoft/ArchScale/blob/main/precision.py
precision.py	https://github.com/microsoft/ArchScale/blob/main/precision.py
pretrain.py	https://github.com/microsoft/ArchScale/blob/main/pretrain.py
pretrain.py	https://github.com/microsoft/ArchScale/blob/main/pretrain.py
utils.py	https://github.com/microsoft/ArchScale/blob/main/utils.py
utils.py	https://github.com/microsoft/ArchScale/blob/main/utils.py
README	https://github.com/microsoft/ArchScale
Code of conduct	https://github.com/microsoft/ArchScale
Contributing	https://github.com/microsoft/ArchScale
MIT license	https://github.com/microsoft/ArchScale
Security	https://github.com/microsoft/ArchScale
	https://github.com/microsoft/ArchScale/blob/main/assets/shooting_stars.png
	https://github.com/microsoft/ArchScale#--archscale--
	https://github.com/microsoft/ArchScale#updates
HyperP	https://arxiv.org/abs/2603.28743
SqrtGate	https://arxiv.org/abs/2603.28743
MuonH	https://whenwen.github.io/wd_blog/public/hyperball-part-1.html
	https://github.com/microsoft/ArchScale/blob/main/assets/scaling_comparison.png
Decoder-Hybrid-Decoder Architectures	https://aka.ms/flashreasoning-paper
poster	https://github.com/microsoft/ArchScale/blob/main/assets/sambay_poster.pdf
Phi-4-mini-flash-reasoning	https://huggingface.co/microsoft/Phi-4-mini-flash-reasoning
	https://github.com/microsoft/ArchScale/blob/main/assets/sambay_arch.png
	https://github.com/microsoft/ArchScale/blob/main/assets/scaling_data_1B_mup_abl_tie.png
	https://github.com/microsoft/ArchScale#features
Gated Memory Unit	https://aka.ms/flashreasoning-paper
YOCO	https://arxiv.org/abs/2405.05254
Differential Attention	https://arxiv.org/pdf/2410.05258
SonicMoE	https://github.com/Dao-AILab/sonic-moe
SqrtGate	https://arxiv.org/abs/2603.28743
HyperP	https://arxiv.org/abs/2603.28743
μP++	https://aka.ms/flashreasoning-paper
MuonH	https://whenwen.github.io/wd_blog/public/hyperball-part-1.html
Muon	https://github.com/microsoft/ArchScale/blob/main/lit_gpt/optim/muon.py
WYSIWYG	https://en.wikipedia.org/wiki/WYSIWYG
TransformerEngine	https://github.com/NVIDIA/TransformerEngine
lm-eval	https://github.com/EleutherAI/lm-evaluation-harness
Proof-Pile	https://github.com/microsoft/ArchScale/blob/main/eval_proofpile.py
LightEval	https://github.com/microsoft/ArchScale/blob/main/eval_reason
plotting scripts	https://github.com/microsoft/ArchScale/blob/main/plots
	https://github.com/microsoft/ArchScale#installation
install.sh	https://github.com/microsoft/ArchScale/blob/main/install.sh
	https://github.com/microsoft/ArchScale#pretraining
Samba	https://github.com/microsoft/Samba/?tab=readme-ov-file#data-preparation
here	https://huggingface.co/datasets/jsun/slimpajama_Llama2_Tokenizer
	https://github.com/microsoft/ArchScale#moe-training
launch_scripts/	https://github.com/microsoft/ArchScale/blob/main/launch_scripts
paper	https://arxiv.org/abs/2603.28743
	https://github.com/microsoft/ArchScale#scaling-flops
BaseHyperparameters	https://github.com/microsoft/ArchScale/blob/main/pretrain.py#L83
setup	https://github.com/microsoft/ArchScale/blob/main/pretrain.py#L172
plotting scripts	https://github.com/microsoft/ArchScale/blob/main/plots
	https://github.com/microsoft/ArchScale#scaling-data
	https://github.com/microsoft/ArchScale#long-context-training
ProLong-64K	https://huggingface.co/datasets/princeton-nlp/prolong-data-64K
here	https://huggingface.co/datasets/jsun/Prolong_64K_v2_Llama2_Tokenizer
	https://github.com/microsoft/ArchScale#evaluation
	https://github.com/microsoft/ArchScale#standard-nlp-benchmarks
	https://github.com/microsoft/ArchScale#proof-pile-evaluation
Proof-Pile	https://huggingface.co/datasets/hoskinson-center/proof-pile
	https://github.com/microsoft/ArchScale#long-context-evaluation
	https://github.com/microsoft/ArchScale#ruler-benchmark
RULER	https://arxiv.org/abs/2404.06654
	https://github.com/microsoft/ArchScale#phonebook-evaluation
Phonebook	https://arxiv.org/abs/2402.01032
	https://github.com/microsoft/ArchScale#reasoning-evaluation
LightEval	https://github.com/huggingface/lighteval
PR	https://github.com/vllm-project/vllm/pull/20702
	https://github.com/microsoft/ArchScale#scaling-analysis
plots/	https://github.com/microsoft/ArchScale/blob/main/plots
	https://github.com/microsoft/ArchScale#citation
	https://github.com/microsoft/ArchScale#license
LICENSE	https://github.com/microsoft/ArchScale/blob/main/LICENSE
	https://github.com/microsoft/ArchScale#acknowledgments
SonicMoE	https://github.com/Dao-AILab/sonic-moe
Samba	https://github.com/microsoft/Samba/
LitGPT	https://github.com/Lightning-AI/litgpt
TinyLlama	https://github.com/jzhang38/TinyLlama
Flash Linear Attention	https://github.com/fla-org/flash-linear-attention
TransformerEngine	https://github.com/NVIDIA/TransformerEngine
Readme	https://github.com/microsoft/ArchScale#readme-ov-file
MIT license	https://github.com/microsoft/ArchScale#MIT-1-ov-file
Code of conduct	https://github.com/microsoft/ArchScale#coc-ov-file
Contributing	https://github.com/microsoft/ArchScale#contributing-ov-file
Security policy	https://github.com/microsoft/ArchScale#security-ov-file
Please reload this page	https://github.com/microsoft/ArchScale
Activity	https://github.com/microsoft/ArchScale/activity
Custom properties	https://github.com/microsoft/ArchScale/custom-properties
34 forks	https://github.com/microsoft/ArchScale/forks
Report repository	https://github.com/contact/report-content?content_url=https%3A%2F%2Fgithub.com%2Fmicrosoft%2FArchScale&report=microsoft+%28user%29
Releases	https://github.com/microsoft/ArchScale/releases
Packages 0	https://github.com/orgs/microsoft/packages?repo_name=ArchScale
Please reload this page	https://github.com/microsoft/ArchScale
Please reload this page	https://github.com/microsoft/ArchScale
Contributors	https://github.com/microsoft/ArchScale/graphs/contributors
Please reload this page	https://github.com/microsoft/ArchScale
Python 95.0%	https://github.com/microsoft/ArchScale/search?l=python
Shell 4.9%	https://github.com/microsoft/ArchScale/search?l=shell
Dockerfile 0.1%	https://github.com/microsoft/ArchScale/search?l=dockerfile
	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.