Load 4bit models 4x faster
Collection
Native bitsandbytes 4bit pre quantized models
•
25 items
•
Updated
•
59
Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
Directly quantized 4bit model with bitsandbytes.
Original source: https://huggingface.co/alpindale/Mistral-7B-v0.2-hf/tree/main used to create the 4bit quantized versions.
We have a Google Colab Tesla T4 notebook for Mistral 7b v2 (32K context length) here: https://colab.research.google.com/drive/1Fa8QVleamfNELceNM9n7SeAGr_hT5XIn?usp=sharing
✨ Finetune for Free
All notebooks are beginner friendly! Add your dataset, click "Run All", and you'll get a 2x faster finetuned model which can be exported to GGUF, vLLM or uploaded to Hugging Face.
| Unsloth supports | Free Notebooks | Performance | Memory use |
|---|---|---|---|
| Gemma 7b | ▶️ Start on Colab | 2.4x faster | 58% less |
| Mistral 7b | ▶️ Start on Colab | 2.2x faster | 62% less |
| Llama-2 7b | ▶️ Start on Colab | 2.2x faster | 43% less |
| TinyLlama | ▶️ Start on Colab | 3.9x faster | 74% less |
| CodeLlama 34b A100 | ▶️ Start on Colab | 1.9x faster | 27% less |
| Mistral 7b 1xT4 | ▶️ Start on Kaggle | 5x faster* | 62% less |
| DPO - Zephyr | ▶️ Start on Colab | 1.9x faster | 19% less |
- This conversational notebook is useful for ShareGPT ChatML / Vicuna templates.
- This text completion notebook is for raw text. This DPO notebook replicates Zephyr.
- * Kaggle has 2x T4s, but we use 1. Due to overhead, 1x T4 is 5x faster.
- Downloads last month
- 146