This model was created as part of my bachelor's thesis, where I fine-tuned the llama3.1:8B language model for generating ABAP code using Unsloth 4-Bit QLoRA.

I don't recommend you use this model, it is pretty bad.

Downloads last month
-
GGUF
Model size
8B params
Architecture
llama
Hardware compatibility
Log In to add your hardware

4-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train timkoehne/ds2-v6-llama3.1-8b-Q4_K_M