ValueError: Can't find 'adapter_config.json' at './results1/checkpoints/0000500' #178
Comments
|
I think this error is due to an incorrect model path './results1/checkpoints/0000500'. Please ensure you have entered the correct path. |
|
the path is correct. I think there are no adapter_config.json in checkpoints. how to solve this? thanks!!
…------------------ 原始邮件 ------------------
发件人: "Shitao ***@***.***>;
发送时间: 2025年1月6日(星期一) 晚上7:27
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [VectorSpaceLab/OmniGen] ValueError: Can't find 'adapter_config.json' at './results1/checkpoints/0000500' (Issue #178)
I think this error is due to an incorrect model path './results1/checkpoints/0000500'. Please ensure you have entered the correct path.
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
|
|
@hebz11 , could you show what files are in that directory? |
|
Hi, Shitao Xiao, the directory have 5 files but not have adapter_config.json
…------------------ 原始邮件 ------------------
发件人: "Shitao ***@***.***>;
发送时间: 2025年1月7日(星期二) 下午4:26
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [VectorSpaceLab/OmniGen] ValueError: Can't find 'adapter_config.json' at './results1/checkpoints/0000500' (Issue #178)
@hebz11 , could you show what files are in that directory? ./results1/checkpoints/0000500
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
|
What are these five files? |
|
Sorry I replied by email, the image can't be loaded on github. |
|
@hebz11 , I think that you are fine-tuning the entire model, rather than lora fine-tuning. You should load the ckpt following: https://github.com/VectorSpaceLab/OmniGen/blob/main/docs/fine-tuning.md#inference |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Dear Author, I use your train.py
but when I done this. and create a new .py to test the model.
root@autodl-container-b3ec4da47b-21563288:~/autodl-tmp/OmniGen# python3 u.py
Model not found, downloading...
Downloaded model to /root/.cache/huggingface/hub/models--Shitao--OmniGen-v1/snapshots/58e249c7c7634423c0ba41c34a774af79aa87889
Loading safetensors
Traceback (most recent call last):
File "/root/miniconda3/lib/python3.12/site-packages/peft/config.py", line 197, in _get_peft_type
config_file = hf_hub_download(
^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 106, in _inner_fn
validate_repo_id(arg_value)
File "/root/miniconda3/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 154, in validate_repo_id
raise HFValidationError(
huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': './results1/checkpoints/0000500'. Use
repo_typeargument if needed.During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/root/autodl-tmp/OmniGen/u.py", line 4, in
pipe.merge_lora("./results1/checkpoints/0000500") # e.g., ./results/toy_finetune_lora/checkpoints/0000200
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/autodl-tmp/OmniGen/OmniGen/pipeline.py", line 98, in merge_lora
model = PeftModel.from_pretrained(self.model, lora_path)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/lib/python3.12/site-packages/peft/peft_model.py", line 325, in from_pretrained
PeftConfig._get_peft_type(
File "/root/miniconda3/lib/python3.12/site-packages/peft/config.py", line 203, in _get_peft_type
raise ValueError(f"Can't find '{CONFIG_NAME}' at '{model_id}'")
ValueError: Can't find 'adapter_config.json' at './results1/checkpoints/0000500'
The text was updated successfully, but these errors were encountered: