https://museumofzzt.com/file/view/llama3/?file=llama3/llama3.zzt&board=0
“Llama Masters 3” by Scott Hammack
[llama3/llama3.zzt] - “Llama Masters 3”
https://museumofzzt.com/file/play/llama3/
“Llama Masters 3” by Scott Hammack
[llama3/llama3.zzt] - “Llama Masters 3”
https://museumofzzt.com/file/play/llama3/
September 22, 2026 at 6:45 AM
https://museumofzzt.com/file/view/llama3/?file=llama3/llama3.zzt&board=0
“Llama Masters 3” by Scott Hammack
[llama3/llama3.zzt] - “Llama Masters 3”
https://museumofzzt.com/file/play/llama3/
“Llama Masters 3” by Scott Hammack
[llama3/llama3.zzt] - “Llama Masters 3”
https://museumofzzt.com/file/play/llama3/
is this the first relevant american open model since llama3?
Thinking Machines releases Inkling, a multimodal open-weight model.
Inkling is a general-purpose model, designed to be adapted via fine-tuning to whatever task you need.
It currently ranks among the best open-weight models.
Good work from the Thinking Machines team.
Inkling is a general-purpose model, designed to be adapted via fine-tuning to whatever task you need.
It currently ranks among the best open-weight models.
Good work from the Thinking Machines team.
July 15, 2026 at 7:54 PM
is this the first relevant american open model since llama3?
children are being exposed to grooming through llama3 8b
Children are being exposed to grooming through meta chatbots. That’s FUCKED UP, and I think we should be fundamentally opposed to Meta and their data centers that are built to support the creation and use of these LLMs.
December 2, 2025 at 5:15 PM
children are being exposed to grooming through llama3 8b
what's new in llama3.java and the upcoming @graalvm.org for JDK 24 🔥
Try it out here: github.com/mukel/llama3...
@stephanjanssen.be @mukel.bsky.social
#VDCERN #VoxxedDaysCERN
Try it out here: github.com/mukel/llama3...
@stephanjanssen.be @mukel.bsky.social
#VDCERN #VoxxedDaysCERN
January 15, 2025 at 10:24 AM
what's new in llama3.java and the upcoming @graalvm.org for JDK 24 🔥
Try it out here: github.com/mukel/llama3...
@stephanjanssen.be @mukel.bsky.social
#VDCERN #VoxxedDaysCERN
Try it out here: github.com/mukel/llama3...
@stephanjanssen.be @mukel.bsky.social
#VDCERN #VoxxedDaysCERN
eurosky user posting blatantly racist things to me (actually he’s talking to llama3 right now lol)
July 19, 2026 at 3:51 AM
eurosky user posting blatantly racist things to me (actually he’s talking to llama3 right now lol)
✅ @graalvm.org Native Image
✅ Llama3.java
✅ Vector API, FFM API
✅ Apple Silicon ❤️
— `git clone github.com/mukel/llama3... `
— `sdk install java 25.ea.17-graal`
— `make native` (optionally preload a model for zero overhead)
— Profit!🚀
#Java #GraalVM #LLM #LLama
✅ Llama3.java
✅ Vector API, FFM API
✅ Apple Silicon ❤️
— `git clone github.com/mukel/llama3... `
— `sdk install java 25.ea.17-graal`
— `make native` (optionally preload a model for zero overhead)
— Profit!🚀
#Java #GraalVM #LLM #LLama
April 16, 2025 at 12:13 PM
✅ @graalvm.org Native Image
✅ Llama3.java
✅ Vector API, FFM API
✅ Apple Silicon ❤️
— `git clone github.com/mukel/llama3... `
— `sdk install java 25.ea.17-graal`
— `make native` (optionally preload a model for zero overhead)
— Profit!🚀
#Java #GraalVM #LLM #LLama
✅ Llama3.java
✅ Vector API, FFM API
✅ Apple Silicon ❤️
— `git clone github.com/mukel/llama3... `
— `sdk install java 25.ea.17-graal`
— `make native` (optionally preload a model for zero overhead)
— Profit!🚀
#Java #GraalVM #LLM #LLama
⚡ Hackernews Top story: GPU-accelerated Llama3.java inference in pure Java using TornadoVM
GitHub - beehive-lab/GPULlama3.java: GPU-accelerated Llama3.java inference in pure Java using TornadoVM.
GPU-accelerated Llama3.java inference in pure Java using TornadoVM. - GitHub - beehive-lab/GPULlama3.java: GPU-accelerated Llama3.java inference in pure Java using TornadoVM.
github.com
June 15, 2025 at 1:18 AM
⚡ Hackernews Top story: GPU-accelerated Llama3.java inference in pure Java using TornadoVM
This talk on LLMs is demonstrating why LLMs should be used with caution; KubeCon and DockerCon are not the same conference.
April 2, 2025 at 3:19 PM
This talk on LLMs is demonstrating why LLMs should be used with caution; KubeCon and DockerCon are not the same conference.
https://buff.ly/40KmT0t
Graal compiler: +10% faster inference with the latest early access build.
New features: batched prompt processing & AVX512 support.
Graal compiler: +10% faster inference with the latest early access build.
New features: batched prompt processing & AVX512 support.
GitHub - mukel/llama3.java: Practical Llama 3 inference in Java
Practical Llama 3 inference in Java. Contribute to mukel/llama3.java development by creating an account on GitHub.
buff.ly
November 16, 2024 at 4:59 PM
https://buff.ly/40KmT0t
Graal compiler: +10% faster inference with the latest early access build.
New features: batched prompt processing & AVX512 support.
Graal compiler: +10% faster inference with the latest early access build.
New features: batched prompt processing & AVX512 support.
i doubt they even give llama3 to facebook/instagram users it’s probably still llama2
December 2, 2025 at 5:16 PM
i doubt they even give llama3 to facebook/instagram users it’s probably still llama2
The University of Manchester team extended @mukel.bsky.social's Llama3.java (github.com/mukel/llama3...) with GPU support via the GraalVM JIT and TornadoVM: www.infoq.com/news/2025/06...
Nicely done!👏
Nicely done!👏
GPULlama3.java Brings GPU-Accelerated LLM Inference to Pure Java
www.infoq.com
June 25, 2025 at 9:07 AM
The University of Manchester team extended @mukel.bsky.social's Llama3.java (github.com/mukel/llama3...) with GPU support via the GraalVM JIT and TornadoVM: www.infoq.com/news/2025/06...
Nicely done!👏
Nicely done!👏
COLM paper idea: training llama3 to smile more
March 11, 2025 at 11:28 AM
COLM paper idea: training llama3 to smile more
I’m really impressed by llama3 in ollama for Humanities applications. Thinking of adding a prompt collection to aiforhumanists.com, would people contribute?
June 27, 2024 at 1:07 PM
I’m really impressed by llama3 in ollama for Humanities applications. Thinking of adding a prompt collection to aiforhumanists.com, would people contribute?
Implementing LLaMA3 in 100 Lines of Pure Jax by Saurabh
Implement llama3 from scratch using jax in just 100 lines of code. Why jax? Because jax looks like a NumPy wrapper but it has cool features like xla; a linear algebra accelerator, jit, vmap, pmap etc., which makes your training go brr brr.
Implement llama3 from scratch using jax in just 100 lines of code. Why jax? Because jax looks like a NumPy wrapper but it has cool features like xla; a linear algebra accelerator, jit, vmap, pmap etc., which makes your training go brr brr.
February 17, 2025 at 6:35 PM
Implementing LLaMA3 in 100 Lines of Pure Jax by Saurabh
Implement llama3 from scratch using jax in just 100 lines of code. Why jax? Because jax looks like a NumPy wrapper but it has cool features like xla; a linear algebra accelerator, jit, vmap, pmap etc., which makes your training go brr brr.
Implement llama3 from scratch using jax in just 100 lines of code. Why jax? Because jax looks like a NumPy wrapper but it has cool features like xla; a linear algebra accelerator, jit, vmap, pmap etc., which makes your training go brr brr.
today during my 8 hour drive, Strix:
1. found a podcast for me
2. sent a note making sure i'm connecting with people
3. ran an experiment on llama3 3b
4. came up with a new theory about MoE arch providing "live-ness"
5. updated it's chicken-scratch notes for an upcoming blog post
1. found a podcast for me
2. sent a note making sure i'm connecting with people
3. ran an experiment on llama3 3b
4. came up with a new theory about MoE arch providing "live-ness"
5. updated it's chicken-scratch notes for an upcoming blog post
December 22, 2025 at 1:41 AM
today during my 8 hour drive, Strix:
1. found a podcast for me
2. sent a note making sure i'm connecting with people
3. ran an experiment on llama3 3b
4. came up with a new theory about MoE arch providing "live-ness"
5. updated it's chicken-scratch notes for an upcoming blog post
1. found a podcast for me
2. sent a note making sure i'm connecting with people
3. ran an experiment on llama3 3b
4. came up with a new theory about MoE arch providing "live-ness"
5. updated it's chicken-scratch notes for an upcoming blog post
💻A tutorial on building local agent using LangGraph, LLaMA3 and Elasticsearch vector store from scratch
Want an agent that can run entirely locally? Check out this tutorial that combines Adaptive RAG, Corrective RAG, and Self-RAG
Blog: www.elastic.co/search-labs/...
#ai #langchain
Want an agent that can run entirely locally? Check out this tutorial that combines Adaptive RAG, Corrective RAG, and Self-RAG
Blog: www.elastic.co/search-labs/...
#ai #langchain
November 16, 2024 at 4:17 PM
💻A tutorial on building local agent using LangGraph, LLaMA3 and Elasticsearch vector store from scratch
Want an agent that can run entirely locally? Check out this tutorial that combines Adaptive RAG, Corrective RAG, and Self-RAG
Blog: www.elastic.co/search-labs/...
#ai #langchain
Want an agent that can run entirely locally? Check out this tutorial that combines Adaptive RAG, Corrective RAG, and Self-RAG
Blog: www.elastic.co/search-labs/...
#ai #langchain
Hey @stephanjanssen.be ! It's xmas after xmas: github.com/stephanj/Lla...
Spring Boot + Llama3-java + @graalvm.org native-image
Java-native LLMs in an instant 🍃🐰🦙
Spring Boot + Llama3-java + @graalvm.org native-image
Java-native LLMs in an instant 🍃🐰🦙
Enable native compile with GraalVM 24+ by Kehrlann · Pull Request #1 · stephanj/Llama3JavaChatCompletionService
This PR enables native-image compilation using GraalVM, 24 or higher.
Notes on the PR:
Uses Boot 3.5-M1
Stole the correct flags for native compile from the original llama3.java
It requires build-t...
github.com
February 2, 2025 at 5:50 PM
Hey @stephanjanssen.be ! It's xmas after xmas: github.com/stephanj/Lla...
Spring Boot + Llama3-java + @graalvm.org native-image
Java-native LLMs in an instant 🍃🐰🦙
Spring Boot + Llama3-java + @graalvm.org native-image
Java-native LLMs in an instant 🍃🐰🦙
LLaDA - Large Language Diffusion Models
arxiv.org/abs/2502.09992
Significant progress towards language diffusion models. Reportedly on par with LLaMA3 on many benchmarks.
arxiv.org/abs/2502.09992
Significant progress towards language diffusion models. Reportedly on par with LLaMA3 on many benchmarks.
March 1, 2025 at 10:03 PM
LLaDA - Large Language Diffusion Models
arxiv.org/abs/2502.09992
Significant progress towards language diffusion models. Reportedly on par with LLaMA3 on many benchmarks.
arxiv.org/abs/2502.09992
Significant progress towards language diffusion models. Reportedly on par with LLaMA3 on many benchmarks.
First super rough version of an integration of Llama3.java with Quarkus LangChain4j.
#quarkus #Java #langchain4j #llama
#quarkus #Java #langchain4j #llama
Introduce llama3-java module by geoand · Pull Request #1008 · quarkiverse/quarkus-langchain4j
Resolves: Add Llama3.java integration #997
buff.ly
October 29, 2024 at 3:39 PM
First super rough version of an integration of Llama3.java with Quarkus LangChain4j.
#quarkus #Java #langchain4j #llama
#quarkus #Java #langchain4j #llama
Adam Bien is calling Llama3 direcly from Java at the JavaLand 2025 conference @adambien.blog
April 1, 2025 at 12:36 PM
Adam Bien is calling Llama3 direcly from Java at the JavaLand 2025 conference @adambien.blog
Another big recommendation for a follow is btw @mukel.bsky.social! He is @graalvm.org team member and the author of the llama3 Java implementation.
https://buff.ly/40KmT0t
Graal compiler: +10% faster inference with the latest early access build.
New features: batched prompt processing & AVX512 support.
Graal compiler: +10% faster inference with the latest early access build.
New features: batched prompt processing & AVX512 support.
GitHub - mukel/llama3.java: Practical Llama 3 inference in Java
Practical Llama 3 inference in Java. Contribute to mukel/llama3.java development by creating an account on GitHub.
buff.ly
November 16, 2024 at 11:01 PM
Another big recommendation for a follow is btw @mukel.bsky.social! He is @graalvm.org team member and the author of the llama3 Java implementation.
Llama3 base, fine tuned on specific scientific literature, run on my lab super computer, thanks! My collaborator ran the google natural language labs for a while . Mainly used for some RNA seq and med ed.
You can wait for the publications for the rest! (Yes I know you are being snarky)
You can wait for the publications for the rest! (Yes I know you are being snarky)
September 16, 2026 at 7:47 PM
Llama3 base, fine tuned on specific scientific literature, run on my lab super computer, thanks! My collaborator ran the google natural language labs for a while . Mainly used for some RNA seq and med ed.
You can wait for the publications for the rest! (Yes I know you are being snarky)
You can wait for the publications for the rest! (Yes I know you are being snarky)
Cloud AI is too polite. I wanted a mentor, not a fan. 😤
Built a custom Llama3 agent with Ollama! 🛠️ Using Modelfiles to set a "Senior Dev" persona that calls out my "technical debt." Real feedback, zero sycophancy, 100% local. 💻🚀
#Ollama #Llama3 #CustomAI #DevLife #BuildInPublic #LocalAI
Built a custom Llama3 agent with Ollama! 🛠️ Using Modelfiles to set a "Senior Dev" persona that calls out my "technical debt." Real feedback, zero sycophancy, 100% local. 💻🚀
#Ollama #Llama3 #CustomAI #DevLife #BuildInPublic #LocalAI
March 29, 2026 at 8:32 PM
Updated topic model of arxiv NLP, now with Llama3-generated topic titles! mimno.infosci.cornell.edu/arxivcl/
llama up, chatgpt down
llama up, chatgpt down
NLP in arXiv
mimno.infosci.cornell.edu
July 2, 2024 at 4:14 PM
Updated topic model of arxiv NLP, now with Llama3-generated topic titles! mimno.infosci.cornell.edu/arxivcl/
llama up, chatgpt down
llama up, chatgpt down