When I tried to load the model locally, I used the code below:
model_path = "MONAI/Llama3-VILA-M3-13B"
model_path = snapshot_download(model_path)
model_name = get_model_name_from_path(model_path)
tokenizer, model, image_processor, context_len = load_pretrained_model(
model_path,
model_name
)
Download successful. I am sure that the downloaded version is the same as the one on hugging face.
However...
Here is the log:
TypeError: load_pretrained_model() missing 1 required positional argument: 'model_name'
And then I modified the code like this:
model_path = "MONAI/Llama3-VILA-M3-8B"
model_path = snapshot_download(model_path)
model_base = model_path + "/" + "llm"
model_name = get_model_name_from_path(model_path)
tokenizer, model, image_processor, context_len = load_pretrained_model(
model_path,
model_base,
model_name
)
Here is the error:
[2025-04-20 14:03:20,295] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Fetching 21 files: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 21/21 [00:00<00:00, 15971.06it/s]
/home/brownradx/.cache/huggingface/hub/models--MONAI--Llama3-VILA-M3-8B/snapshots/df60e0276e2ae10624c86dabe909847a03b2a5cb
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:05<00:00, 1.38s/it]
Loading LoRA weights from /home/brownradx/.cache/huggingface/hub/models--MONAI--Llama3-VILA-M3-8B/snapshots/df60e0276e2ae10624c86dabe909847a03b2a5cb
Traceback (most recent call last):
File "/home/brownradx/miniconda3/envs/vila/lib/python3.10/site-packages/peft/config.py", line 260, in _get_peft_type
config_file = hf_hub_download(
File "/home/brownradx/miniconda3/envs/vila/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 106, in _inner_fn
validate_repo_id(arg_value)
File "/home/brownradx/miniconda3/envs/vila/lib/python3.10/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': '/home/brownradx/.cache/huggingface/hub/models--MONAI--Llama3-VILA-M3-8B/snapshots/df60e0276e2ae10624c86dabe909847a03b2a5cb'. Use `repo_type` argument if needed.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/home/brownradx/Documents/Xinye_projects/vila/backend/model_runner.py", line 15, in <module>
tokenizer, model, image_processor, context_len = load_pretrained_model(
File "/home/brownradx/Documents/Xinye_projects/LLaVA/llava/model/builder.py", line 130, in load_pretrained_model
model = PeftModel.from_pretrained(model, model_path)
File "/home/brownradx/miniconda3/envs/vila/lib/python3.10/site-packages/peft/peft_model.py", line 439, in from_pretrained
PeftConfig._get_peft_type(
File "/home/brownradx/miniconda3/envs/vila/lib/python3.10/site-packages/peft/config.py", line 266, in _get_peft_type
raise ValueError(f"Can't find '{CONFIG_NAME}' at '{model_id}'")
ValueError: Can't find 'adapter_config.json' at '/home/brownradx/.cache/huggingface/hub/models--MONAI--Llama3-VILA-M3-8B/snapshots/df60e0276e2ae10624c86dabe909847a03b2a5cb'
Two errors:
- Can not find 'adapter_config.json'.
- huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/home/brownradx/.cache/huggingface/hub/models--MONAI--Llama3-VILA-M3-8B/snapshots/df60e0276e2ae10624c86dabe909847a03b2a5cb'. Use
repo_type argument if needed.
What should I do about it?
Did I miss the file adapter_config.json or it's something else that I didn't notice?
When I tried to load the model locally, I used the code below:
Download successful. I am sure that the downloaded version is the same as the one on hugging face.
However...
Here is the log:
TypeError: load_pretrained_model() missing 1 required positional argument: 'model_name'And then I modified the code like this:
Here is the error:
Two errors:
repo_typeargument if needed.What should I do about it?
Did I miss the file adapter_config.json or it's something else that I didn't notice?