#bigcodeproject search results

Come by @ServiceNowRSRCH booth for a discussion with our Researcher Harm de Vries. He will present his poster about the Big code initiative and responsible development of large language models for code. #NeurIPS2022 #bigcodeproject

cathe_martin's tweet image. Come by @ServiceNowRSRCH booth for a discussion with our Researcher Harm de Vries. He will present his poster about the Big code initiative and responsible development of large language models for code. #NeurIPS2022 #bigcodeproject

Today is an important day for the #BigCodeProject. We published our Governance Card that provides an unprecedented level of transparency into the development that went into the StarCoder model we announced last week, and more. While each of the outputs from the project was…

BigCode was organized around the value of openness; open sharing of datasets and models, and also transparency of the project organization, motivations, and decisions! We're making all this information available in our new Governance Card 📚 1/4 🧵 hf.co/datasets/bigco…



60. Such a nice round number 🤗 Some #bigcodeproject tips - with thanks to @lvwerra for an excellent presentation at #dinacon22 - here: hacknight.dinacon.ch/project/62

loleg's tweet image. 60. Such a nice round number 🤗 
Some #bigcodeproject tips - with thanks to @lvwerra for an excellent presentation at #dinacon22 - here: hacknight.dinacon.ch/project/62

Call for collaborators: Help us improve the #BigCodeProject Code LLM evaluation harness, by adding more benchmarks and features ✨ #OpenScience #OpenSource #OpenAccess

Introducing the BigCode Evaluation Harness for Code LLMs: github.com/bigcode-projec… Inspired by the lm-evaluation-harness from @AiEleuther, it ensures ease-of-use, reproducibility and efficiency. Let’s explore its key features 🧵:

BigCodeProject's tweet image. Introducing the BigCode Evaluation Harness for Code LLMs:

github.com/bigcode-projec…

Inspired by the lm-evaluation-harness from @AiEleuther, it ensures ease-of-use, reproducibility and efficiency. Let’s explore its key features 🧵:


We're excited to announce our collaboration with @huggingface to develop state-of-the-art LLMs for code. Code LLMs enable the completion & synthesis of code & work across a wide range of domains, tasks, & programming languages. #BigCodeProject Read more: servicenow.com/blogs/2022/big…

print("Hello world! 🎉") Excited to announce the BigCode project led by @ServiceNowRSRCH and @huggingface! In the spirit of BigScience we aim to develop large language models for code in an open and responsible way. Join here: bigcode-project.org/docs/about/joi… A thread with our goals🧵

BigCodeProject's tweet image. print("Hello world! 🎉")

Excited to announce the BigCode project led by @ServiceNowRSRCH and @huggingface! In the spirit of BigScience we aim to develop large language models for code in an open and responsible way.

Join here: bigcode-project.org/docs/about/joi…

A thread with our goals🧵


Exciting developments in the #BigCodeProject. ICYMI Our goal is to train a large language model for code. Our SantaCoder model was 1B parameters. This one is somewhat larger. 😁

We started training something big and the daily training updates have degenerated to weather reports 🌦:

BigCodeProject's tweet image. We started training something big and the daily training updates have degenerated to weather reports 🌦:


Proud to have led the working group for Legal, Ethics, Governance on #BigCodeProject. Very grateful to all the community that leaned in and to @harmdevries77 @lvwerra @Carlos_MFerr @YJernite for all the collaborations and contributions.

Introducing: 💫StarCoder StarCoder is a 15B LLM for code with 8k context and trained only on permissive data in 80+ programming languages. It can be prompted to reach 40% pass@1 on HumanEval and act as a Tech Assistant. Try it here: shorturl.at/cYZ06r Release thread🧵

BigCodeProject's tweet image. Introducing: 💫StarCoder

StarCoder is a 15B LLM for code with 8k context and trained only on permissive data in 80+ programming languages. It can be prompted to reach 40% pass@1 on HumanEval and act as a Tech Assistant.

Try it here: shorturl.at/cYZ06r

Release thread🧵


Congratulations to @LoubnaBenAllal1 and our fellow contributors from the #BigCodeProject on this best paper award today at the Deep Learning 4 Code #DL4Code workshop at #ICLR2023.

Congratulations to the @BigCodeProject contributors on receiving the best paper award for “🎅 SantaCoder - Don’t reach for the Stars!”, today at the @DL4Code workshop held at @iclr_conf. Amazing work and well deserved recognition. Workshop: dl4c.github.io/papers/



🗓️SAVE THE DATE: Our next #BigCodeProject webinar takes place on Thursday, JUNE 8th. BigCode has raised the bar on transparency and open governance in partnership with the machine learning and open source communities towards the responsible development and use of Code LLMs, and…

Next week we'll host an online session about how StarCoder was built and show-casing interesting demos that people have built since! Date: Thursday June 8th, 6-7:30pm CEST (9-10:30am PST) Link: servicenow.zoom.us/j/99103734103 If you have an interesting demo to present please reach out!



Come learn about what it took to build #BigCodeProject #StarCoder and about our newest model (yes, another one). There will also be a few demos of apps built by the #Community. Webinar starts at 09:00 PST today. #OpenAccess #Responsible #Transparency #Code #LLM

Reminder that the online session is starting in 90min and we have an exciting model we'll release as well! Link: servicenow.zoom.us/j/99103734103



Code LLMs have the potential to help professional and citizen developers with coding new applications. AI Researchers are invited to collaborate on 1) Evaluation suite 2) Responsible dataset development 3) Faster training & inference methods for LLMs. #BigCodeProject #OpenSource

print("Hello world! 🎉") Excited to announce the BigCode project led by @ServiceNowRSRCH and @huggingface! In the spirit of BigScience we aim to develop large language models for code in an open and responsible way. Join here: bigcode-project.org/docs/about/joi… A thread with our goals🧵

BigCodeProject's tweet image. print("Hello world! 🎉")

Excited to announce the BigCode project led by @ServiceNowRSRCH and @huggingface! In the spirit of BigScience we aim to develop large language models for code in an open and responsible way.

Join here: bigcode-project.org/docs/about/joi…

A thread with our goals🧵


Interesting insights on determining the Compute-Optimal Model Size from @harmdevries77 and researchers on the #BigCodeProject -> #LLM #Compute #Chinchilla #ScalingLaws

This analysis is the result of discussions with many amazing collaborators at the @BigCodeProject. Come join us if you're interested in these research topics!



"Am I in The Stack?" is an open governance tool from the #BigCodeProject for developers to search for their source code repositories that are included in The Stack dataset. Learn more in the #Announcement 🧵below.

Is your code in 📑 The Stack? Check if your repositories are in the dataset and a large language models for code will learn from them! hf.co/spaces/bigcode… You don't want your code to be part of The Stack? Follow the opt-out instruction and we'll remove it!



I’d love to attend but can’t make it there. Any chance you can host a livestream? @lvwerra are we going to have a #BigCodeProject demo at the showcase?


Just in time for the holiday break, we’ve released a bunch of surprise gifts from the BigCode Community! There’s a lot of work that went into these efforts by the #BigCodeProject - THANK YOU to everyone involved. Read the thread below for details. #OpenSource #ResponsibleAI

Announcing a holiday gift: 🎅SantaCoder - a 1.1B multilingual LM for code that outperforms much larger open-source models on both left-to-right generation and infilling! Demo: hf.co/spaces/bigcode… Paper: hf.co/datasets/bigco… Attribution: hf.co/spaces/bigcode… A🧵:

BigCodeProject's tweet image. Announcing a holiday gift: 🎅SantaCoder - a 1.1B multilingual LM for code that outperforms much larger open-source models on both left-to-right generation and infilling!

Demo: hf.co/spaces/bigcode…
Paper: hf.co/datasets/bigco…
Attribution: hf.co/spaces/bigcode…

A🧵:


If you’ve contributed to #OpenSource in the past, there’s a chance your code is in The Stack dataset & will be used to train Large Language Models for code. Use “Am I in The Stack?” with your GitHub account to check your status or opt-out.👇🏻 #BigCodeProject #ResponsibleAI #LLM

Is your code in 📑 The Stack? Check if your repositories are in the dataset and a large language models for code will learn from them! hf.co/spaces/bigcode… You don't want your code to be part of The Stack? Follow the opt-out instruction and we'll remove it!



The #BigCodeProject was formed as an open scientific collaboration working towards the responsible development and use of Large Language Models for Code. In the spirit of open governance, the community has now published a Governance Card for the project. #AI #Transparency

BigCode was organized around the value of openness; open sharing of datasets and models, and also transparency of the project organization, motivations, and decisions! We're making all this information available in our new Governance Card 📚 1/4 🧵 hf.co/datasets/bigco…



Exciting work from the #OpenScience #BigCodeProject community. 400+ Researchers from >30 countries since Sep 26, 2022. Lots of work still to be done including training 10B+ Code LLMs. Researchers can join the collaboration here: bigcode-project.org/docs/about/joi… #ResponsibleAI

We release all models and intermediate checkpoints on the Hugging Face Hub and load the via the revision: huggingface.co/bigcode/santac… The compute for these experiments was sponsored by @ServiceNowRSRCH's research cluster.

BigCodeProject's tweet image. We release all models and intermediate checkpoints on the Hugging Face Hub and load the via the revision:

huggingface.co/bigcode/santac…

The compute for these experiments was sponsored by @ServiceNowRSRCH's research cluster.


Impressive collaboration! 🤝 Can't wait to read all about it. #AI #BigCodeProject #MachineLearning #Collaboration


ICYMI Here is the link to #watch the #BigCodeProject webinar from June 8th, 2023 where StarCoder team members walked through the details of how the StarCoder 15B parameter LLM was developed, along with some fantastic demos of apps powered by StarCoder... youtu.be/sQFWE__JAsA

Reminder that the online session is starting in 90min and we have an exciting model we'll release as well! Link: servicenow.zoom.us/j/99103734103



Come learn about what it took to build #BigCodeProject #StarCoder and about our newest model (yes, another one). There will also be a few demos of apps built by the #Community. Webinar starts at 09:00 PST today. #OpenAccess #Responsible #Transparency #Code #LLM

Reminder that the online session is starting in 90min and we have an exciting model we'll release as well! Link: servicenow.zoom.us/j/99103734103



🗓️SAVE THE DATE: Our next #BigCodeProject webinar takes place on Thursday, JUNE 8th. BigCode has raised the bar on transparency and open governance in partnership with the machine learning and open source communities towards the responsible development and use of Code LLMs, and…

Next week we'll host an online session about how StarCoder was built and show-casing interesting demos that people have built since! Date: Thursday June 8th, 6-7:30pm CEST (9-10:30am PST) Link: servicenow.zoom.us/j/99103734103 If you have an interesting demo to present please reach out!



Call for collaborators: Help us improve the #BigCodeProject Code LLM evaluation harness, by adding more benchmarks and features ✨ #OpenScience #OpenSource #OpenAccess

Introducing the BigCode Evaluation Harness for Code LLMs: github.com/bigcode-projec… Inspired by the lm-evaluation-harness from @AiEleuther, it ensures ease-of-use, reproducibility and efficiency. Let’s explore its key features 🧵:

BigCodeProject's tweet image. Introducing the BigCode Evaluation Harness for Code LLMs:

github.com/bigcode-projec…

Inspired by the lm-evaluation-harness from @AiEleuther, it ensures ease-of-use, reproducibility and efficiency. Let’s explore its key features 🧵:


Today is an important day for the #BigCodeProject. We published our Governance Card that provides an unprecedented level of transparency into the development that went into the StarCoder model we announced last week, and more. While each of the outputs from the project was…

BigCode was organized around the value of openness; open sharing of datasets and models, and also transparency of the project organization, motivations, and decisions! We're making all this information available in our new Governance Card 📚 1/4 🧵 hf.co/datasets/bigco…



The #BigCodeProject was formed as an open scientific collaboration working towards the responsible development and use of Large Language Models for Code. In the spirit of open governance, the community has now published a Governance Card for the project. #AI #Transparency

BigCode was organized around the value of openness; open sharing of datasets and models, and also transparency of the project organization, motivations, and decisions! We're making all this information available in our new Governance Card 📚 1/4 🧵 hf.co/datasets/bigco…



Impressive collaboration! 🤝 Can't wait to read all about it. #AI #BigCodeProject #MachineLearning #Collaboration


Congratulations to @LoubnaBenAllal1 and our fellow contributors from the #BigCodeProject on this best paper award today at the Deep Learning 4 Code #DL4Code workshop at #ICLR2023.

Congratulations to the @BigCodeProject contributors on receiving the best paper award for “🎅 SantaCoder - Don’t reach for the Stars!”, today at the @DL4Code workshop held at @iclr_conf. Amazing work and well deserved recognition. Workshop: dl4c.github.io/papers/



Hugging Face and ServiceNow Research have launched StarCoder, a free AI model for code generation trained on over 80 programming languages and text from GitHub repositories. #AI #CodeGeneration #BigCodeProject techcrunch.com/2023/05/04/hug…


Proud to have led the working group for Legal, Ethics, Governance on #BigCodeProject. Very grateful to all the community that leaned in and to @harmdevries77 @lvwerra @Carlos_MFerr @YJernite for all the collaborations and contributions.

Introducing: 💫StarCoder StarCoder is a 15B LLM for code with 8k context and trained only on permissive data in 80+ programming languages. It can be prompted to reach 40% pass@1 on HumanEval and act as a Tech Assistant. Try it here: shorturl.at/cYZ06r Release thread🧵

BigCodeProject's tweet image. Introducing: 💫StarCoder

StarCoder is a 15B LLM for code with 8k context and trained only on permissive data in 80+ programming languages. It can be prompted to reach 40% pass@1 on HumanEval and act as a Tech Assistant.

Try it here: shorturl.at/cYZ06r

Release thread🧵


Interesting insights on determining the Compute-Optimal Model Size from @harmdevries77 and researchers on the #BigCodeProject -> #LLM #Compute #Chinchilla #ScalingLaws

This analysis is the result of discussions with many amazing collaborators at the @BigCodeProject. Come join us if you're interested in these research topics!



Exciting developments in the #BigCodeProject. ICYMI Our goal is to train a large language model for code. Our SantaCoder model was 1B parameters. This one is somewhat larger. 😁

We started training something big and the daily training updates have degenerated to weather reports 🌦:

BigCodeProject's tweet image. We started training something big and the daily training updates have degenerated to weather reports 🌦:


I’d love to attend but can’t make it there. Any chance you can host a livestream? @lvwerra are we going to have a #BigCodeProject demo at the showcase?


The #BigCodeProject is gaining momentum

It’s exciting to see the @Europarl_EN Innovation Lab team taking interest in the #BigCodeProject - this validates our Mission. We’ve already had 13k+ downloads of The Stack since Oct’22 and 🎅SantaCoder 5k+ in the first 30d since 🎄. bigcode-project.org #OpenGovernance #AI



It’s exciting to see the @Europarl_EN Innovation Lab team taking interest in the #BigCodeProject - this validates our Mission. We’ve already had 13k+ downloads of The Stack since Oct’22 and 🎅SantaCoder 5k+ in the first 30d since 🎄. bigcode-project.org #OpenGovernance #AI

What's better about @BigCodeProject is that it's properly open, not "just" convenient with a chat interface or popular. That means you get to understand how it's done, in particular what data (including potentially yours) is being used, cf huggingface.co/datasets/bigco…

utopiah's tweet image. What's better about @BigCodeProject is that it's properly open, not "just" convenient with a chat interface or popular.

That means you get to understand how it's done, in particular what data (including potentially yours) is being used, cf huggingface.co/datasets/bigco…


Exciting work from the #OpenScience #BigCodeProject community. 400+ Researchers from >30 countries since Sep 26, 2022. Lots of work still to be done including training 10B+ Code LLMs. Researchers can join the collaboration here: bigcode-project.org/docs/about/joi… #ResponsibleAI

We release all models and intermediate checkpoints on the Hugging Face Hub and load the via the revision: huggingface.co/bigcode/santac… The compute for these experiments was sponsored by @ServiceNowRSRCH's research cluster.

BigCodeProject's tweet image. We release all models and intermediate checkpoints on the Hugging Face Hub and load the via the revision:

huggingface.co/bigcode/santac…

The compute for these experiments was sponsored by @ServiceNowRSRCH's research cluster.


Just in time for the holiday break, we’ve released a bunch of surprise gifts from the BigCode Community! There’s a lot of work that went into these efforts by the #BigCodeProject - THANK YOU to everyone involved. Read the thread below for details. #OpenSource #ResponsibleAI

Announcing a holiday gift: 🎅SantaCoder - a 1.1B multilingual LM for code that outperforms much larger open-source models on both left-to-right generation and infilling! Demo: hf.co/spaces/bigcode… Paper: hf.co/datasets/bigco… Attribution: hf.co/spaces/bigcode… A🧵:

BigCodeProject's tweet image. Announcing a holiday gift: 🎅SantaCoder - a 1.1B multilingual LM for code that outperforms much larger open-source models on both left-to-right generation and infilling!

Demo: hf.co/spaces/bigcode…
Paper: hf.co/datasets/bigco…
Attribution: hf.co/spaces/bigcode…

A🧵:


Come by @ServiceNowRSRCH booth for a discussion with our Researcher Harm de Vries. He will present his poster about the Big code initiative and responsible development of large language models for code. #NeurIPS2022 #bigcodeproject

cathe_martin's tweet image. Come by @ServiceNowRSRCH booth for a discussion with our Researcher Harm de Vries. He will present his poster about the Big code initiative and responsible development of large language models for code. #NeurIPS2022 #bigcodeproject

60. Such a nice round number 🤗 Some #bigcodeproject tips - with thanks to @lvwerra for an excellent presentation at #dinacon22 - here: hacknight.dinacon.ch/project/62

loleg's tweet image. 60. Such a nice round number 🤗 
Some #bigcodeproject tips - with thanks to @lvwerra for an excellent presentation at #dinacon22 - here: hacknight.dinacon.ch/project/62

If you’ve contributed to #OpenSource in the past, there’s a chance your code is in The Stack dataset & will be used to train Large Language Models for code. Use “Am I in The Stack?” with your GitHub account to check your status or opt-out.👇🏻 #BigCodeProject #ResponsibleAI #LLM

Is your code in 📑 The Stack? Check if your repositories are in the dataset and a large language models for code will learn from them! hf.co/spaces/bigcode… You don't want your code to be part of The Stack? Follow the opt-out instruction and we'll remove it!



Come by @ServiceNowRSRCH booth for a discussion with our Researcher Harm de Vries. He will present his poster about the Big code initiative and responsible development of large language models for code. #NeurIPS2022 #bigcodeproject

cathe_martin's tweet image. Come by @ServiceNowRSRCH booth for a discussion with our Researcher Harm de Vries. He will present his poster about the Big code initiative and responsible development of large language models for code. #NeurIPS2022 #bigcodeproject

60. Such a nice round number 🤗 Some #bigcodeproject tips - with thanks to @lvwerra for an excellent presentation at #dinacon22 - here: hacknight.dinacon.ch/project/62

loleg's tweet image. 60. Such a nice round number 🤗 
Some #bigcodeproject tips - with thanks to @lvwerra for an excellent presentation at #dinacon22 - here: hacknight.dinacon.ch/project/62

Loading...

Something went wrong.


Something went wrong.


United States Trends