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
8
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for tavtav/Pyg-Llama-8B-1M-0.25

Quantizations
1 model