turboderp's picture
Create README.md
7335632
EXL2 quants of [TinyLlama-1.1B-32k (1.1B)](https://huggingface.co/Doctor-Shotgun/TinyLlama-1.1B-32k).
[2.50 bits per weight](https://huggingface.co/turboderp/TinyLlama-1B-32k-exl2/tree/2.5bpw)
[2.70 bits per weight](https://huggingface.co/turboderp/TinyLlama-1B-32k-exl2/tree/2.7bpw)
[3.00 bits per weight](https://huggingface.co/turboderp/TinyLlama-1B-32k-exl2/tree/3.0bpw)
[3.50 bits per weight](https://huggingface.co/turboderp/TinyLlama-1B-32k-exl2/tree/3.5bpw)
[4.00 bits per weight](https://huggingface.co/turboderp/TinyLlama-1B-32k-exl2/tree/4.0bpw)
[4.65 bits per weight](https://huggingface.co/turboderp/TinyLlama-1B-32k-exl2/tree/4.65bpw)
[5.00 bits per weight](https://huggingface.co/turboderp/TinyLlama-1B-32k-exl2/tree/5.0bpw)
[6.00 bits per weight](https://huggingface.co/turboderp/TinyLlama-1B-32k-exl2/tree/6.0bpw)
[7.00 bits per weight](https://huggingface.co/turboderp/TinyLlama-1B-32k-exl2/tree/7.0bpw)
[8.00 bits per weight](https://huggingface.co/turboderp/TinyLlama-1B-32k-exl2/tree/8.0bpw)
[measurement.json](https://huggingface.co/turboderp/TinyLlama-1B-32k-exl2/blob/main/measurement.json)