ValueError: The checkpoint you are trying to load has model type llava_mistral but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

[dainini]

Reminder

• I have read the above rules and searched the existing issues.

System Info

• llamafactory version: 0.9.1
• Platform: Linux-5.4.0-177-generic-x86_64-with-glibc2.31
• Python version: 3.11.11
• PyTorch version: 2.3.0+cu121 (GPU)
• Transformers version: 4.45.2
• Datasets version: 3.1.0
• Accelerate version: 1.0.1
• PEFT version: 0.12.0
• TRL version: 0.9.6
• GPU type: NVIDIA A100 80GB PCIe
• DeepSpeed version: 0.14.0
• Bitsandbytes version: 0.43.1
• vLLM version: 0.5.0

Reproduction

llamafactory-cli train examples/train_lora/llavamed1_5_lora_dpo.yaml 
[2025-01-30 21:19:56,796] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[INFO|2025-01-30 21:20:00] llamafactory.hparams.parser:355 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.bfloat16
[INFO|configuration_utils.py:673] 2025-01-30 21:20:00,204 >> loading configuration file /hdd0/dain/models/llava-med-v1.5-mistral-7b/config.json
Traceback (most recent call last):
  File "/home/dain/.conda/envs/llama-factory/lib/python3.11/site-packages/transformers/models/auto/configuration_auto.py", line 1023, in from_pretrained
    config_class = CONFIG_MAPPING[config_dict["model_type"]]
                   ~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/dain/.conda/envs/llama-factory/lib/python3.11/site-packages/transformers/models/auto/configuration_auto.py", line 725, in __getitem__
    raise KeyError(key)
KeyError: 'llava_mistral'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/home/dain/.conda/envs/llama-factory/bin/llamafactory-cli", line 8, in <module>
    sys.exit(main())
             ^^^^^^
  File "/home/dain/.conda/envs/llama-factory/lib/python3.11/site-packages/llamafactory/cli.py", line 112, in main
    run_exp()
  File "/home/dain/.conda/envs/llama-factory/lib/python3.11/site-packages/llamafactory/train/tuner.py", line 56, in run_exp
    run_dpo(model_args, data_args, training_args, finetuning_args, callbacks)
  File "/home/dain/.conda/envs/llama-factory/lib/python3.11/site-packages/llamafactory/train/dpo/workflow.py", line 43, in run_dpo
    tokenizer_module = load_tokenizer(model_args)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/dain/.conda/envs/llama-factory/lib/python3.11/site-packages/llamafactory/model/loader.py", line 69, in load_tokenizer
    config = load_config(model_args)
             ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/dain/.conda/envs/llama-factory/lib/python3.11/site-packages/llamafactory/model/loader.py", line 119, in load_config
    return AutoConfig.from_pretrained(model_args.model_name_or_path, **init_kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/dain/.conda/envs/llama-factory/lib/python3.11/site-packages/transformers/models/auto/configuration_auto.py", line 1025, in from_pretrained
    raise ValueError(
ValueError: The checkpoint you are trying to load has model type `llava_mistral` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

Others

No response