can't load any models in textgen with "no module named" error

[WildPowerHammer]

I have few gptq and gguf models, when i try to run gptq i have this:

2024-08-06 00:47:26 ERROR:Failed to load the model.
Traceback (most recent call last):
  File "/nix/store/1zzqmn5cl5c8dcbv37xp8xvvii892015-textgen-patchedSrc/modules/ui_model_menu.py", line 201, in load_model_wrapper
    shared.model, shared.tokenizer = load_model(shared.model_name, loader)
                                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/nix/store/1zzqmn5cl5c8dcbv37xp8xvvii892015-textgen-patchedSrc/modules/models.py", line 79, in load_model
    output = load_func_map[loader](model_name)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/nix/store/1zzqmn5cl5c8dcbv37xp8xvvii892015-textgen-patchedSrc/modules/models.py", line 318, in AutoGPTQ_loader
    import modules.AutoGPTQ_loader
  File "/nix/store/1zzqmn5cl5c8dcbv37xp8xvvii892015-textgen-patchedSrc/modules/AutoGPTQ_loader.py", line 3, in <module>
    from auto_gptq import AutoGPTQForCausalLM, BaseQuantizeConfig
ModuleNotFoundError: No module named 'auto_gptq'

Similar with other model loaders, just changes the name of module that not found

If i try to run gguf model i have

2024-08-06 00:52:34 INFO:Loading dolphin-2.6-mistral-7b.Q6_K.gguf...
2024-08-06 00:52:34 INFO:llama.cpp weights detected: /home/digital_dominus/.textgen/state/models/dolphin-2.6-mistral-7b.Q6_K.gguf
2024-08-06 00:52:34 INFO:Cache capacity is 0 bytes
/nix/store/rfpyasrilnfv9xmv5z50jnyv5w12178y-textgen/bin/textgen: line 26: 126248 Illegal instruction     (core dumped) /nix/store/7hpffz24mjm12y5ymd2is43lxl7nf27b-python3-3.11.6-env/bin/python /nix/store/1zzqmn5cl5c8dcbv37xp8xvvii892015-textgen-patchedSrc/server.py $@ --model-dir $HOME/.textgen/state/models/ --lora-dir $HOME/.textgen/state/loras/

I'm absolutely unsure what i can try to fix this, for me looks like i somehow broke very reproducible installation process and now i'm here

P.S. If anyone can at least recommend me some other ways to run local models, I will be very grateful.