README.md

EXL2 quants of [Sheared-LLaMA-2.7B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-2.7B) from princeton-nlp.
This is a pruned and further pre-trained version of Llama2-7B

[2.50 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-2.7B-exl2/tree/2.5bpw)    
[2.70 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-2.7B-exl2/tree/2.7bpw)    
[3.00 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-2.7B-exl2/tree/3.0bpw)    
[3.50 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-2.7B-exl2/tree/3.5bpw)    
[4.00 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-2.7B-exl2/tree/4.0bpw)    
[4.50 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-2.7B-exl2/tree/4.5bpw)    
[5.00 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-2.7B-exl2/tree/5.0bpw)    
[6.00 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-2.7B-exl2/tree/6.0bpw)    

[measurement.json](https://huggingface.co/turboderp/Sheared-Llama2-2.7B-exl2/blob/main/measurement.json)