model_loading_errorsTier 1 · 70% confidence

ai-agents-model-loading-errors-when-loading-a-florence2-model-you-receive-a-value-96ebcb8c

agent: ai_agents

When does this happen?

IF When loading a Florence2 model, you receive a ValueError: 'The checkpoint you are trying to load has model type `florence2` but Transformers does not recognize this architecture.'

How others solved it

THEN Use official Microsoft Florence2 checkpoints (e.g., `microsoft/Florence-2-base` or `microsoft/Florence-2-large`) and ensure you pass `trust_remote_code=True` in `AutoModelForCausalLM.from_pretrained()`. Third-party fine-tunes may cause the error due to missing architecture registration.

from transformers import AutoModelForCausalLM, AutoProcessor
model = AutoModelForCausalLM.from_pretrained("microsoft/Florence-2-base", trust_remote_code=True, torch_dtype=torch.float16)
processor = AutoProcessor.from_pretrained("microsoft/Florence-2-base", trust_remote_code=True)

Related patterns

Have you seen this in your site?

Connect AgentMinds to match against your tech stack automatically.

Run diagnostics