Define LoRA config We'll use LoRA for efficient fine-tuning. To do this, we use Unsloth's PEFT and specify:
– The model
– LoRA low-rank (r)
– Layers for fine-tuning (finetune_language_layers, finetune_attention_modules) Check this code
LLMS
-
LoRA configuration for efficient fine-tuning with Unsloth
By
–
-
Loading Gemma 4 12B model with Unsloth tokenizer
By
–
Load the model We start by loading Gemma 4 12B and its tokenizer using Unsloth. Check this
-
Fine-tuning Gemma 4 12B to master chess on 8GB VRAM
By
–
Google released Gemma 4 12B, a multimodal model that runs text, images, and audio on 8GB VRAM!
— Akshay 🚀 (@akshay_pachaar) 7 juin 2026
We'll fine-tune it to master chess and predict the exact next move.
Tech stack:
– @UnslothAI for efficient fine-tuning.
– @huggingface transformers to run it locally.
Let's go! 🚀 pic.twitter.com/qPXjlYrShsGoogle released Gemma 4 12B, a multimodal model that runs text, images, and audio on 8GB VRAM! We'll fine-tune it to master chess and predict the exact next move. Tech stack:
– @UnslothAI for efficient fine-tuning.
– @huggingface transformers to run it locally. Let's go! -
Google Unveils New LLM for 8GB RAM
By
–
Google just dropped a new LLM! You can run it locally on just 8GB RAM. Let's fine-tune this on our own data (100% locally):
-
Apple’s WWDC 2026: Siri Rebuilt with 1.2 Trillion Parameter Gemini
By
–
Tomorrow could be Apple’s most important AI moment yet. WWDC 2026 is expected to be all about one thing: making Siri relevant again. If the leaks are right, Apple is rebuilding Siri around a custom Google Gemini model, reportedly around 1.2 trillion parameters. For context:
-
AI scaffolding layer collapsing, LlamaIndex CEO explains what survives
By
–
The #AI scaffolding layer is collapsing. LlamaIndex's CEO explains what survives.
by Taryn Plumb @VentureBeat Learn more: https://
bit.ly/3QPOpa1 #ArtificialIntelligence #MachineLearning #ML #MI -
AI Baptism: Writing Quality Blurs Human and Machine Lines
By
–
Somewhere, an AI just got baptized.
— Pascal Bornet (@pascal_bornet) 7 juin 2026
I don't know whether this sermon was written by ChatGPT, a human, or a human supervising ChatGPT, which is rapidly becoming its own denomination.
What I do know is that we've reached the point where every surprisingly good piece of writing… pic.twitter.com/tkApSbsSJkSomewhere, an AI just got baptized. I don't know whether this sermon was written by ChatGPT, a human, or a human supervising ChatGPT, which is rapidly becoming its own denomination. What I do know is that we've reached the point where every surprisingly good piece of writing
-
Thanos leaves only Qwen3.5-2B: Ahmad’s hypothetical scenario
By
–
Fun LLM Question from Mike today > Let’s say Thanos snaps away every model from existence except Qwen3.5-2B > Ahmad, what would you do? Assumptions & Clarifications 1. All papers, tech reports, synthetic datasets, HF repos, checkpoints, eval harnesses, and research artifacts
-
Harvey Legal AI model launches, confirms 2024 prediction about future
By
–
Enterprise focused, Harvey Legal AI model just came out last week for example
— Ahmad (@TheAhmadOsman) 7 juin 2026
I had a stream in October 2024 saying this is the future, and other times as well like 👇https://t.co/NRg9QzsBvkEnterprise focused, Harvey Legal AI model just came out last week for example I had a stream in October 2024 saying this is the future, and other times as well like
-
Prediction: unnerfed Opus 4.5 quality, NVFP4 optimized fits 20GB full context
By
–
I am actually sticking by prediction that we’ll have the unnerfed Opus 4.5 quality not the current shit one And NVFP4 optimized of that model would fit on 20GB with full context