I did not build the model based on docker
m3/demo/gradio_m3.py
Line 295-297
##############
self.tokenizer, self.model, self.image_processor, self.context_len = load_pretrained_model(
model_path, model_name
)
##############
I think load_pretrained_model missing parameters
then I repaired with
##############
self.tokenizer, self.model, self.image_processor, self.context_len = load_pretrained_model(
model_path, None, model_name
)
##############
But I got an error when executing the code：
OSError: Can't load tokenizer for '/root/autodl-tmp/cache/hub/models--MONAI--Llama3-VILA-M3-8B/snapshots/df60e0276e2ae10624c86dabe909847a03b2a5cb'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure '/root/autodl-tmp/cache/hub/models--MONAI--Llama3-VILA-M3-8B/snapshots/df60e0276e2ae10624c86dabe909847a03b2a5cb' is the correct path to a directory containing all relevant files for a LlamaTokenizer tokenizer.
I did not build the model based on docker
m3/demo/gradio_m3.py
Line 295-297
##############
self.tokenizer, self.model, self.image_processor, self.context_len = load_pretrained_model(
model_path, model_name
)
##############
I think load_pretrained_model missing parameters
then I repaired with
##############
self.tokenizer, self.model, self.image_processor, self.context_len = load_pretrained_model(
model_path, None, model_name
)
##############
But I got an error when executing the code：
OSError: Can't load tokenizer for '/root/autodl-tmp/cache/hub/models--MONAI--Llama3-VILA-M3-8B/snapshots/df60e0276e2ae10624c86dabe909847a03b2a5cb'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure '/root/autodl-tmp/cache/hub/models--MONAI--Llama3-VILA-M3-8B/snapshots/df60e0276e2ae10624c86dabe909847a03b2a5cb' is the correct path to a directory containing all relevant files for a LlamaTokenizer tokenizer.