Problem in deploying on hugging face hub

Models
1

Hi!
I fine-tuned nllb model on my data using Lora.
but after uploading it on hugging face hub, I couldn’t deploy it and hugging face is not showing any deploy button for me.
these are the files in my model that I uploaded.
Can someone help me with this issue?

Screenshot (240)
Screenshot (240)1920×1430 321 KB

2

Hi,

It looks like the repository contains the adapter weights.

To load the entire model (base model with adapter weights), you can use the AutoPeftModelForSeq2Seq class:

from peft import AutoPeftModelForSeq2SeqLM

base_model_id = "facebook/nllb-200-distilled-600M"
adapter_model_id = "your-adapter-repo"

peft_model = AutoPeftModelForSeq2SeqLM.from_pretrained(base_model_id, adapter_model_id)

# now you can call the merge_and_unload method which returns a regular NLLB model which you can use for inference
model = peft_model.merge_and_unload()
3

I got this error. my base model is nllb 3.3:
During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File “/home/ali/veirtual_env/mahdi.py”, line 6, in
peft_model = AutoPeftModelForSeq2SeqLM.from_pretrained(base_model_id, adapter_model_id)
File “/home/ali/checkpoint/model-training/vnev/lib/python3.10/site-packages/peft/auto.py”, line 69, in from_pretrained
peft_config = PeftConfig.from_pretrained(pretrained_model_name_or_path, **kwargs)
File “/home/ali/checkpoint/model-training/vnev/lib/python3.10/site-packages/peft/config.py”, line 109, in from_pretrained
raise ValueError(f"Can’t find ‘{CONFIG_NAME}’ at ‘{pretrained_model_name_or_path}’")
ValueError: Can’t find ‘adapter_config.json’ at ‘facebook/nllb-200-3.3B’

4

Hi, is this problem already fixed? I have the same problem.