Article
Kimi K2.5: Still Worth It After Two Weeks?
•
8
Maxime Labonne PRO
mlabonne
AI & ML interests
Post-training, model editing, quantization
Recent Activity
new activity 4 days ago
mlabonne/open-perfectblend:Dead prompt-only and empty-assistant rows in train splitOrganizations
published an article 25 days ago
published an article 28 days ago
Article
Train AI models with Unsloth and Hugging Face Jobs for FREE
- +4
•
88
published an article about 1 month ago
Article
Qwen3.5: Nobody Agrees on Attention Anymore
•
14
published an article about 1 month ago
Article
MiniMax-M2.5: The $1/hour Frontier Model
•
1
published an article about 1 month ago
Article
GLM-5: China's First Public AI Company Ships a Frontier Model
•
1
published an article about 1 year ago
Article
The Large Language Model Course
•
225
published an article over 1 year ago
Article
Decoding Strategies in Large Language Models
•
109
published an article over 1 year ago
Article
Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth
•
369
published an article over 1 year ago
Article
The Rise of Agentic Data Generation
•
89
published an article almost 2 years ago
Article
Uncensor any LLM with abliteration
•
812
published an article almost 2 years ago
Article
Fine-tune Llama 3 with ORPO
•
240
published an article almost 2 years ago
Article
Create Mixtures of Experts with MergeKit
•
27
published an article about 2 years ago
Article
Merge Large Language Models with mergekit
•
152