LG AI EXAONE3 -> llamafy + 8K Context length -> 4bit awq quantized model

tested in vllm, just for use

''' vllm serve lee5j/EXAONE3-IT8k-llamafy-awq --enforce-eager --gpu-memory-utilization 0.99 '''

origin model : LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct

Safetensors

Model size

1.77B params

Tensor type

I32

FP16

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for lee5j/EXAONE3-IT8k-llamafy-awq

Base model

Quantized

(1)

this model