Chain of thought Llama-3.1-8b
Basicaly just trained on KingNish/reasoning-base-20k but added a little **$$CONCLUSION$$** at the end so the answer can be seperated. My PC is currently broken, so I had to make do with google colab
Uploaded model
- Developed by: Khawn2u
- License: apache-2.0
- Finetuned from model : unsloth/Meta-Llama-3.1-8B-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 43
Model tree for Khawn2u/Llama-3.1-8b-Chain-Of-Thought-GGUF
Base model
meta-llama/Llama-3.1-8B
Quantized
unsloth/Meta-Llama-3.1-8B-bnb-4bit