📢 Hi all! The #InstructLab Community is evolving to better align with technical changes, with the project components being separated and relocated. Here is the full announcement: blog.instructlab.ai/2025/09/inst...

Thank you for all your participation and contributions in the past year! 🐶

Will instruclab.ai's Synthetic Data-Based LLM Fine-Tuning Make the Process More Accessible? InstructLab.ai implements the large-scale alignment for the chatbots concept(LAB), which intends to overcome the scalability challenges in the instruction-tuning phase of a large language model…

Will instruclab.ai's Synthetic Data-Based LLM Fine-Tuning Make the Process More Accessible? buff.ly/4Pql2iZ
#instructlab #llm #genai

How to Make LLM fine-tuning accessible with InstructLab Even as AI technologies rapidly evolve, the foundational challenge remains: how can we make these systems understand and work with our specif...

#AI #InstructLab #Large #Language #Models #Red #Hat #AI #customization #Cedric #Clyburn […]

An image promoting the event with the following details: AI Plumbers Conference 2nd edition 15th June, Berlin, GLC Campus Marta Blaszczyk and Karsten Gresch, Red Hat (with their profile pics) "From laptop to production: building and scaling LLM-enabled apps with open source tools" On the side are logos of sponsors/partners including Red Hat, Hugging Face, Berlin Buzzwords, and AI Foundry.

Join us at AI Plumbers Conference on June 15 in Berlin!

From Red Hat, Marta and Karsten will present how to go from a notebook sketch to a production-ready LLM app using #opensource tools like Podman AI Lab and #InstructLab

Details and registration: lu.ma/vqx423ct

Check out the AI track sessions on #RHSummit Community Day! events.experiences.redhat.com/widget/redha...

We have topics ranging from #Docling to #TrustyAI, inferencing to features stores, topped with your favourite #InstructLab tools & #Granite models. Register & add the sessions to your schedule!

InstructLab Core v0.22.2
🫵 adds llama-cpp-python v0.3.2 meaning we now support Granite 3.0 GGUF models
🫵 adds a new config class, so please run ilab config init for proper functionality
bit.ly/4h57I70
#instructlab #genai #rhelai

We'll be at #fossnorth in #Gothenburg next week, April 14-15! Learn about #InstructLab in the hands-on workshop on day 1 with @cybette.bsky.social

foss-north.se/2025/schedul...

【第2回】InstructLabを試すための環境構築手順（Docker編）｜quoota 🔰概要 InstructLabは、大規模言語モデル（LLM）に新しい知識やスキルを学習させるためのフレームワークです。 GPT-4などの高価なモデルを使わずに、独自のタクソノミー構造と合成データ生成により、安価かつ柔軟にモデルを微調整できるのが特徴です。 本記事では、InstructLabを実際に動かすためのDocker環境構築手順を紹介します。 🎯 目的（執筆の背景） Instruc...

note.com/qoota5278/n/...

Instructlabの試してみたい方に向けて書きました。

#Instructlab

Synthetic data: A secret ingredient for better language models It's increasingly clear that the quality of a large language model (LLM) is hugely dependent on the quality of the data used during training.

Learn about Synthetic data: a secret ingredient for better language models - and the approach #InstructLab takes, with @cedricclyburn.bsky.social and @cybette.bsky.social

www.redhat.com/en/blog/synt...

instructlab.ai Uses Synthetic Data to Reduce Complexity of Fine-Tuning LLMs InstructLab.ai implements the large-scale alignment for the chatbots concept(LAB), which intends to overcome the scalability challenges in the instruction-tuning phase of a large language model (LLM)....

Hear from @olimpiupop.bsky.social at @infoq.com on how #InstructLab uses synthetic data to reduce complexity of fine-tuning LLMs: www.infoq.com/news/2025/03...

Why Red Hat Thinks AI’s Future Is Small Language Models Developers long ago realized monolithic applications aren’t ideal — Red Hat contends developers need to apply that learning to GenAI.

Check out why #RedHat thinks AI's future is Small Language Models, and the role #InstructLab plays - in this article by @lorainelawson.bsky.social at @thenewstack.io: thenewstack.io/why-red-hat-...

Releases · instructlab/instructlab InstructLab Core package. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data. - instructlab/instructlab

** #InstructLab Core v0.24.z and v0.23.z minor releases **

A couple of minor releases for Core:
- fix batch sizing for SDG (0.24.2 & 0.23.3)
- fix a missing python package dependency, and error-handling for "ilab taxonomy diff" (0.24.3 & 0.23.4)

Changelogs: github.com/instructlab/...

A screenshot of the instructlab.ai webpage, with the InstructLab logo, description "A new community-based approach to build truly open-source LLMs", and links to various resources

Join IBM Cloud Paris meetup for a "Deep dive InstructLab" with M'hamed Benabid, on April 9, 2025. Details and RSVP: www.meetup.com/ibm-cloud-pa...

#watsonx #instructlab

Applying Open Source Methods to Building and Training Large Language Models - Carol Chen & JJ Asghar YouTube video by All Things Open

ICYMI: Here's @jjasghar.bsky.social and @cybette.bsky.social with "Applying #OpenSource Methods to Building and Training Large Language Models" at @allthingsopen.bsky.social 2024 in Raleigh, check it out - www.youtube.com/watch?v=UK0Z...

#allthingsopen #instructlab

How to Install #Instructlab + #VLLM with #Nvidia #Cuda Support on Ubuntu 22.04

I had the pleasure of chatting with @katherined.bsky.social, host of the #OpenatIntel podcast, at @allthingsopen.bsky.social last fall:

"Democratizing AI: Collaborative AI Development with #InstructLab"

openatintel.podbean.com/e/democratiz...

Release v0.24.0 · instructlab/instructlab Features vLLM has been updated from 0.6.6.post1 to 0.7.2. llama_cpp_python has been bumped from 0.3.2 to 0.3.6 Served models can now be accessed using short names derived from their path, not just...

** #InstructLab Core v0.24.x Releases **

New releases this month for Core: 0.24.0 and 0.24.1
- vLLM & llama_cpp_python version bumps
- access served models using short names

Changelogs:
- github.com/instructlab/...
- github.com/instructlab/...

Thanks to all who've contributed to the releases!

How open source can democratize AI YouTube video by IBM Technology

Bring on "boring AI."

And the use of it for self-hosted models fine-tuned on your data.

Máirín Duffy chats #InstructLab with Malcolm Gladwell for Smart Talks with #IBM

youtu.be/SkXgG6ksKTA?...

Last night, I installed Red Hat’s open-source AI project #InstructLab, downloaded some models, and ran the chat locally. 🙌🏽

From a methodological perspective, I’ll read the MIT-IBM research paper on LAB (Large-scale Alignment for Chatbots) to better understand the project’s underlying mechanisms.

#InstructLab at @cfgmgmtcamp.bsky.social

Presentation: "Open Source AI and InstructLab" - JJ Asghar, Feb 4 (Tues), 14:50 - 15:40 in B.Con cfp.cfgmgmtcamp.org/ghent2025/ta...

Workshop: "InstructLab workshop" - Feb 5 (Wed), starting at 13:00 in B.3.013 cfp.cfgmgmtcamp.org/ghent2025/ta...

FOSDEM 2025 : Red Hat and IBM Activities

If you're at #FOSDEM this weekend and the fringe events following it, check out this great list of talks on AI, LLMs, #InstructLab, and more!

community.ibm.com/community/us...

Release v0.23.0 · instructlab/instructlab v0.23.0 Breaking Changes llama-cpp-python has been bumped to 0.3.2. This allows for serving of Granite 3.0 GGUF Models. With this change, some previous handling of context window size has been mod...

** InstructLab Core v0.23.0 Release **

* ilab data generate -dt allowing you to run commands in the background
* ilab model upload: upload models to HF, S3 & OCI compatible registries

Full changelog: github.com/instructlab/...
Announcement: groups.google.com/a/instructla...

#InstructLab

Join us at 11AM ET on January 23, 2025 for IBM TechXchange Day: Virtual Agents Virtual Agents Day provides an in-depth look at IBM’s latest AI announcements at its annual TechXchange Conference.

Learn about #InstructLab at IBM TechXchange Dev Day: Virtual Agents tomorrow (Jan 23)! It's a virtual event and there'll be workshop instances for folks to try out InstructLab and see how easy fine-tuning a model can be.

Details & registration: ibmtechxchange-virtual-agents.bemyapp.com

Join Michele Dolfi and me at #RedHat Summit Connect Zurich tomorrow to hear about #Docling, #InstructLab, and more! Details and RSVP: www.redhat.com/en/summit/co...

Release v0.22.2 · instructlab/instructlab What's Changed fix: upgrade trl usage to align with v0.12+ (backport #2805) by @mergify in #2806 fix is_taxonomy_file and get_taxonomy_diff type issue (backport #2849) by @mergify in #2898 add --h...

** InstructLab Core v0.22.2 Release **

- adds llama-cpp-python v0.3.2 => now supports Granite 3.0 GGUF models
- adds a new config class => please run ilab config init for proper functionality

Changelog: github.com/instructlab/...

Announcement: groups.google.com/a/instructla...

#instructlab

Banner for Red Hat Summit Connect indicating location and date (Zürich, January 15, 2025) plus the Red Hat logo.

Join us at #RHSummit: Connect Zürich on Jan 15 to hear from from Michele Dolfi and @cybette.bsky.social about #InstructLab powered by #Docling!

Full agenda and registration: www.redhat.com/en/summit/co...

#opensource #documentAI #Zurich

InstructLab in watsonx.ai https://bit.ly/49dLuwY
#instructlab #aiml #llm #genai

RHEL AI in action: Streamline AI workflows with RAG, LAB, and RAGLAB
https://red.ht/4eLZZcg
#rhelai #aiml #instructlab #llm #genai

Ladoo - the InstructLab dog - wearing a Santa hat, against a festive background with a Christmas tree & a fireplace with hanging socks. There's snow falling outside as seen from the window.

We celebrate the end of 2024 with an exciting milestone - we have published our first community model! Find out how it works and try out the model for yourself: blog.instructlab.ai/2024/12/comm...

Thanks for your support throughout the year, see you in 2025!

#InstructLab

InstructLab, How do I use this thing? – InstructLab A new community-based approach to build truly open-source LLMs

InstructLab, How do I use this thing?
https://bit.ly/3OnM5T4
#genai #instructlab #aiml