|
EXL2 quants of Llama2-13B |
|
|
|
[2.50 bits per weight](https://huggingface.co/turboderp/Llama2-13B-exl2/tree/2.5bpw) |
|
[3.00 bits per weight](https://huggingface.co/turboderp/Llama2-13B-exl2/tree/3.0bpw) |
|
[3.50 bits per weight](https://huggingface.co/turboderp/Llama2-13B-exl2/tree/3.5bpw) |
|
[4.00 bits per weight](https://huggingface.co/turboderp/Llama2-13B-exl2/tree/4.0bpw) |
|
[4.65 bits per weight](https://huggingface.co/turboderp/Llama2-13B-exl2/tree/4.65bpw) |
|
[5.00 bits per weight](https://huggingface.co/turboderp/Llama2-13B-exl2/tree/5.0bpw) |
|
[6.00 bits per weight](https://huggingface.co/turboderp/Llama2-13B-exl2/tree/6.0bpw) |
|
[8.00 bits per weight](https://huggingface.co/turboderp/Llama2-13B-exl2/tree/8.0bpw) |
|
|
|
[measurement.json](https://huggingface.co/turboderp/Llama2-13B-exl2/blob/main/measurement.json) |