Instructions to use NoNameFactory/llama-3-Beomi-Open_Ko-8b-it-4bit-callcenter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NoNameFactory/llama-3-Beomi-Open_Ko-8b-it-4bit-callcenter with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("NoNameFactory/llama-3-Beomi-Open_Ko-8b-it-4bit-callcenter", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
metadata
base_model: beomi/Llama-3-Open-Ko-8B-Instruct-preview
language:
- en
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
Uploaded model
- Developed by: NoNameFactory
- License: apache-2.0
- Finetuned from model : beomi/Llama-3-Open-Ko-8B-Instruct-preview
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
