Mistral Support

[fakerybakery]

Hi,
Does this project support Mistral?
Thanks!

[pprp]

No actually, I got error:

Traceback (most recent call last):
  File "main.py", line 118, in <module>
    main()
  File "main.py", line 90, in main
    prune_sparsegpt(args, model, tokenizer, device, prune_n=prune_n, prune_m=prune_m, layer_no=idx)
  File "/home/user/miniconda3/envs/py38/lib/python3.8/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/data2/user/workspace/PRUNE/GBLM-Pruner/lib/prune.py", line 513, in prune_sparsegpt
    gpts[name].fasterprune(args.sparsity_ratio, prune_n=prune_n, prune_m=prune_m, percdamp=0.01, blocksize=128)
  File "/data2/user/workspace/PRUNE/GBLM-Pruner/lib/sparsegpt.py", line 66, in fasterprune
    H = torch.linalg.cholesky(H)
torch._C._LinAlgError: linalg.cholesky: The factorization could not be completed because the input is not positive-definite (the leading minor of order 1 is not positive-definite).

[bhavyashahh]

Try to increase the dampening factor (cdamp) to avoid this non positive definite issue of the Hession matrix.