Native bitsandbytes 4bit pre quantized models
Unsloth AI
company
AI & ML interests
Hey! We're focusing on making AI more accessible to everyone!
Organization Card
About org cards
Unsloth makes fine-tuning of LLMs 2.2x faster and use 80% less VRAM!
Join our Discord server! 🦥 And our open source Github repo is here!
Unsloth support includes | Free Notebooks | Performance | Memory use |
---|---|---|---|
Llama-3 8b | ▶️ Start on Colab | 2x faster | 60% less |
Gemma 7b | ▶️ Start on Colab | 2.4x faster | 58% less |
Mistral 7b | ▶️ Start on Colab | 2.2x faster | 62% less |
Collections
2
-
unsloth/llama-3-8b-Instruct-bnb-4bit
Text Generation • Updated • 310k • 85 -
unsloth/mistral-7b-instruct-v0.2-bnb-4bit
Text Generation • Updated • 90.9k • 26 -
unsloth/mistral-7b-instruct-v0.3-bnb-4bit
Text Generation • Updated • 11.9k • 9 -
unsloth/Phi-3-mini-4k-instruct-bnb-4bit
Text Generation • Updated • 95.6k • 13