Instructions to use xsa-dev/hugs_llama3_technique_ft_8bit_Q8_0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xsa-dev/hugs_llama3_technique_ft_8bit_Q8_0 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("xsa-dev/hugs_llama3_technique_ft_8bit_Q8_0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Uploaded model
- Developed by: xsa-dev
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 30
Hardware compatibility
Log In to add your hardware
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for xsa-dev/hugs_llama3_technique_ft_8bit_Q8_0
Base model
meta-llama/Meta-Llama-3-8B Quantized
unsloth/llama-3-8b-bnb-4bit