Checkpoint model error - Githubissues

modelscope / ms-swift

Use PEFT or Full-parameter to finetune 400+ LLMs or 100+ MLLMs. (LLM: Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, Gemma2, ...; MLLM: Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL, Phi3.5-Vision, ...)

Apache License 2.0

4.34k stars 381 forks source link

I fine tuned qwen2_vl model for ocr system. I would like predict for one image. I get this error."Can't instantiate a processor, a tokenizer, an image processor or a feature extractor for this model. Make sure the repository contains the files of at least one of those processing classes" File content is as: Screenshot 2024-11-15 152455

I give error this line code model, tokenizer = get_model_tokenizer(model_type, model_kwargs={'device_map': 'auto'},model_id_or_path=ckpt_dir)

How ı can solution this problem?

Thank you everyone

modelscope / ms-swift

Checkpoint model error #2459