🌴 Gemma Goan Q&A Bot

❌ Model failed to load: Could not load model Reubencf/gemma3-goan-finetuned with any of the following classes: (<class 'transformers.models.auto.modeling_auto.AutoModelForCausalLM'>, <class 'transformers.models.gemma3.modeling_gemma3.Gemma3ForConditionalGeneration'>). See the original errors:

while loading with AutoModelForCausalLM, an error is thrown: Traceback (most recent call last): File "/usr/local/lib/python3.10/site-packages/transformers/pipelines/base.py", line 292, in infer_framework_load_model model = model_class.from_pretrained(model, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 600, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 317, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 5177, in from_pretrained model.load_adapter( File "/usr/local/lib/python3.10/site-packages/transformers/integrations/peft.py", line 307, in load_adapter self._dispatch_accelerate_model( File "/usr/local/lib/python3.10/site-packages/transformers/integrations/peft.py", line 558, in _dispatch_accelerate_model dispatch_model( File "/usr/local/lib/python3.10/site-packages/accelerate/big_modeling.py", line 383, in dispatch_model raise ValueError( ValueError: We need an offload_dir to dispatch this model according to this device_map, the following submodules need to be offloaded: model.language_model.layers.20, model.language_model.layers.21, model.language_model.layers.22, model.language_model.layers.23, model.language_model.layers.24, model.language_model.layers.25, model.language_model.layers.26, model.language_model.layers.27, model.language_model.layers.28, model.language_model.layers.29, model.language_model.layers.30, model.language_model.layers.31, model.language_model.layers.32, model.language_model.layers.33, model.language_model.norm, model.language_model.rotary_emb, model.language_model.rotary_emb_local.

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/usr/local/lib/python3.10/site-packages/transformers/pipelines/base.py", line 310, in infer_framework_load_model model = model_class.from_pretrained(model, **fp32_kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py", line 600, in from_pretrained return model_class.from_pretrained( File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 317, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 5177, in from_pretrained model.load_adapter( File "/usr/local/lib/python3.10/site-packages/transformers/integrations/peft.py", line 307, in load_adapter self._dispatch_accelerate_model( File "/usr/local/lib/python3.10/site-packages/transformers/integrations/peft.py", line 558, in _dispatch_accelerate_model dispatch_model( File "/usr/local/lib/python3.10/site-packages/accelerate/big_modeling.py", line 504, in dispatch_model raise ValueError( ValueError: You are trying to offload the whole model to the disk. Please use the disk_offload function instead.

while loading with Gemma3ForConditionalGeneration, an error is thrown: Traceback (most recent call last): File "/usr/local/lib/python3.10/site-packages/transformers/pipelines/base.py", line 292, in infer_framework_load_model model = model_class.from_pretrained(model, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 317, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 5177, in from_pretrained model.load_adapter( File "/usr/local/lib/python3.10/site-packages/transformers/integrations/peft.py", line 307, in load_adapter self._dispatch_accelerate_model( File "/usr/local/lib/python3.10/site-packages/transformers/integrations/peft.py", line 558, in _dispatch_accelerate_model dispatch_model( File "/usr/local/lib/python3.10/site-packages/accelerate/big_modeling.py", line 383, in dispatch_model raise ValueError( ValueError: We need an offload_dir to dispatch this model according to this device_map, the following submodules need to be offloaded: model.language_model.layers.8, model.language_model.layers.9, model.language_model.layers.10, model.language_model.layers.11, model.language_model.layers.12, model.language_model.layers.13, model.language_model.layers.14, model.language_model.layers.15, model.language_model.layers.16, model.language_model.layers.17, model.language_model.layers.18, model.language_model.layers.19, model.language_model.layers.20, model.language_model.layers.21, model.language_model.layers.22, model.language_model.layers.23, model.language_model.layers.24, model.language_model.layers.25, model.language_model.layers.26, model.language_model.layers.27, model.language_model.layers.28, model.language_model.layers.29, model.language_model.layers.30, model.language_model.layers.31, model.language_model.layers.32, model.language_model.layers.33, model.language_model.norm, model.language_model.rotary_emb, model.language_model.rotary_emb_local.

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/usr/local/lib/python3.10/site-packages/transformers/pipelines/base.py", line 310, in infer_framework_load_model model = model_class.from_pretrained(model, **fp32_kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 317, in _wrapper return func(*args, **kwargs) File "/usr/local/lib/python3.10/site-packages/transformers/modeling_utils.py", line 5177, in from_pretrained model.load_adapter( File "/usr/local/lib/python3.10/site-packages/transformers/integrations/peft.py", line 307, in load_adapter self._dispatch_accelerate_model( File "/usr/local/lib/python3.10/site-packages/transformers/integrations/peft.py", line 558, in _dispatch_accelerate_model dispatch_model( File "/usr/local/lib/python3.10/site-packages/accelerate/big_modeling.py", line 504, in dispatch_model raise ValueError( ValueError: You are trying to offload the whole model to the disk. Please use the disk_offload function instead.