Latest posts tagged with #gemma2 on Bluesky
Fine‑Tuning Large Language Models for Low‑Resource Languages
October 2025 study shows a repeatable workflow to fine‑tune Gemma 2 with culturally curated data, boosting AI for a low‑resource language. Read more: getnews.me/fine-tuning-large-langua... #gemma2 #lowresource
Google's new open model, Gemma 2, is here and it's a monster. 🚀
The 27B model is outperforming competitors twice its size. It's built for developers and researchers who need top-tier, efficient AI that runs almost anywhere.
#AI #Gemma2 #Google #OpenSource #LLM #DevTools
📌 pin.it/2KAXfxe3i
Gemma 3 Tutorial for Beginners – Google’s Most Powerful Open AI Google has introduced Gemma 3...
habr.com/en/articles/896290/
#gemma #gemma2 #gemma3 #google #google #api #google #ai #google #ai #studio
Event Attributes
Wow! I didn't really like Gemma 2, but Gemma 3, released today, is awesome. It comes in four sizes, 1b, 4b, 12b and 27b. It's super fast and except for the 1b version it can even handle images.
The 27B version apparently outperforms both DeepSeek v3 and LLaMA3-405 on the ChatbotArena benchmark […]
Open models dominate AI app development! 🚀 Slashdata reports ~66% of devs use them vs. 41% for proprietary & 24% in-house. What's your team's experience? What models are you using?
#AI #ML #OpenModels #Gemma2 #Gemini #ChatGPT
My Saturday #buildinpublic
I am doing a #Gemma2 > Android integration.
Pretty happy with a 2 day part time effort!
Sweet points:
• Ollama
• Open #LLM
• 9B parameter size
• Cloud GPU acceleration
Nicer GUI next!
I can see the privacy use cases 🕵️ since we control the whole API
#Gemmaverse
I've been having a lot of fun over the break.
Things I've been playing with:
- agentic LLMs
- local LLMs
Have to say #Ollama is pretty fun, one of my favourite places to access Gemma2.
Doing a 🗾 to English translation demo with a quantised Gemma2 2B tonight!
#Gemmaverse #Gemma2
🎯 #OpenSource Language Model Platform Launch
🔧 Leverages #vLLM technology with custom #GPU scheduler for running various #LLM models
🤖 Supports major models: #Llama3 (405B/70B/8B), #Qwen2 72B, #Mixtral, #Gemma2, #Jamba15, #Phi3
https://glhf.chat/
🤖 Compatible with major models: #Llama3 405B/70B/8B, #Qwen2 72B, #Mixtral 8x22B, #Gemma2 27B, #Phi3, and more
💻 Features include:
- #OpenAI compatible #API
- Custom-built #GPU scheduler
- Support for full-weight and 4-bit AWQ repos
- Multi-tenant architecture for cost efficiency
Open-Source LLM Platform: Run Models Up to 405B Parameters 🚀
#glhfchat launches platform enabling users to run #opensource #LLM models up to 405B parameters on #GPU clusters. Supports #vLLM architecture, including #Llama3, #Qwen2, #Mixtral, and #Gemma2. Free during beta
glhf.chat/landing/home
Image of the Trevi fountain
Image of the colosseum
When in Rome… you do science! ✨
But you also see the sights 😍
Attending the GEMMA2 workshop this week! Excited for this multidisciplinary workshop with topics ranging from #GravitationalWaves to #DarkMatter 😎
#GEMMA2 #Astrophysics
Published new comparison:
Choosing the Best locally hosted #LLM for #Perplexica:
#Llama3, #Llama3.1, #MistralNemo, #Gemma2, #Qwen2, #Phi3 or #Command-r?
www.glukhov.org/post/2024/08...
#AI #self-hosted
#AI #gemma #gemma2 #GenerativeAI Google releases new ‘open’ AI models with a focus on safety: Google has released a trio of new, “open” generative AI models that it’s calling “safer,” “smaller” and “more transparent” than most — a bold claim, to be sure. They’re additions to Google’s Gemma 2…
