Experimental Test Model of Llama-3-8B (base)
Finetuned using the ChatML formatting. Only 50% of epoch 1 was done out of two epochs.
Extended to 1 Million context using the PoSE technique.
- Downloads last month
- 35
Experimental Test Model of Llama-3-8B (base)
Finetuned using the ChatML formatting. Only 50% of epoch 1 was done out of two epochs.
Extended to 1 Million context using the PoSE technique.