Successful installation leads to error during execution

[steph280]

Expected Behavior:
Launch of program

Actual Behavior:
(MagicQuill) C:\Users\VR2\Desktop\MagicQuill> python gradio_run.py
Total VRAM 24576 MB, total RAM 32684 MB
pytorch version: 2.1.2+cu118
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 3090 : native
Using pytorch cross attention
['C:\Users\VR2\Desktop\MagicQuill', 'C:\Users\VR2\.conda\envs\MagicQuill\python310.zip', 'C:\Users\VR2\.conda\envs\MagicQuill\DLLs', 'C:\Users\VR2\.conda\envs\MagicQuill\lib', 'C:\Users\VR2\.conda\envs\MagicQuill', 'C:\Users\VR2\.conda\envs\MagicQuill\lib\site-packages', 'editable.llava-1.2.2.post1.finder.path_hook', 'C:\Users\VR2\Desktop\MagicQuill\MagicQuill']
Traceback (most recent call last):
File "C:\Users\VR2.conda\envs\MagicQuill\lib\site-packages\transformers\utils\hub.py", line 385, in cached_file
resolved_file = hf_hub_download(
File "C:\Users\VR2.conda\envs\MagicQuill\lib\site-packages\huggingface_hub\utils_validators.py", line 106, in inner_fn
validate_repo_id(arg_value)
File "C:\Users\VR2.conda\envs\MagicQuill\lib\site-packages\huggingface_hub\utils_validators.py", line 160, in validate_repo_id
raise HFValidationError(
huggingface_hub.errors.HFValidationError: Repo id must use alphanumeric chars or '-', '', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'C:\Users\VR2\Desktop\MagicQuill\models\llava-v1.5-7b-finetune-clean'.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\Users\VR2\Desktop\MagicQuill\gradio_run.py", line 21, in
llavaModel = LLaVAModel()
File "C:\Users\VR2\Desktop\MagicQuill\MagicQuill\llava_new.py", line 26, in init
self.tokenizer, self.model, self.image_processor, self.context_len = load_pretrained_model(
File "C:\Users\VR2\Desktop\MagicQuill\MagicQuill\LLaVA\llava\model\builder.py", line 116, in load_pretrained_model
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
File "C:\Users\VR2.conda\envs\MagicQuill\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 758, in from_pretrained
tokenizer_config = get_tokenizer_config(pretrained_model_name_or_path, **kwargs)
File "C:\Users\VR2.conda\envs\MagicQuill\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 590, in get_tokenizer_config
resolved_config_file = cached_file(
File "C:\Users\VR2.conda\envs\MagicQuill\lib\site-packages\transformers\utils\hub.py", line 450, in cached_file
raise EnvironmentError(
OSError: Incorrect path_or_model_id: 'C:\Users\VR2\Desktop\MagicQuill\models\llava-v1.5-7b-finetune-clean'. Please provide either the path to a local folder or the repo_id of a model on the Hub.

(MagicQuill) C:\Users\VR2\Desktop\MagicQuill>

---

Additional Context/Details

---

Environment

• OS: Windows
• Version: 11
• Any Relevant Dependencies:

---

[tristan88888]

From the main installation steps:

Follow the following guide to set up the environment.

git clone repo. Please don't forget the --recursive flag. Otherwise, you will find LLaVA submodule missing.
git clone --recursive https://github.com/magic-quill/MagicQuill.git
cd MagicQuill

[zliucz]

Check issue#54.