qwen1.5 support?

[anan1213095357]

root@a:~/qwen/qwen.cpp/qwen_cpp# python3 convert.py -i /root/qwen/Qwen1.5-1.8B -t q4_0 -o qwen1_8b.bin
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Traceback (most recent call last):
File "/root/qwen/qwen.cpp/qwen_cpp/convert.py", line 262, in
main()
File "/root/qwen/qwen.cpp/qwen_cpp/convert.py", line 256, in main
convert(f, args.model_name_or_path, dtype=args.type)
File "/root/qwen/qwen.cpp/qwen_cpp/convert.py", line 230, in convert
QwenConverter.convert(f, model, tokenizer, ggml_type)
File "/root/qwen/qwen.cpp/qwen_cpp/convert.py", line 182, in convert
cls.dump_config(f, model.config, model.generation_config, tokenizer, ggml_type)
File "/root/qwen/qwen.cpp/qwen_cpp/convert.py", line 198, in dump_config
tokenizer.im_start_id,
AttributeError: 'Qwen2TokenizerFast' object has no attribute 'im_start_id'

[dwojcik92]

Similar issue here:

python3 qwen.cpp/qwen_cpp/convert.py -i Qwen1.5-MoE-A2.7B-Chat   -o Qwen1.5-MoE-A2.7B-Chat.gguf   -t q4_0
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████| 8/8 [00:14<00:00,  1.79s/it]
Traceback (most recent call last):
  File "/home/dwojcik/HF-to-GGUF_converter/qwen.cpp/qwen_cpp/convert.py", line 262, in <module>
    main()
  File "/home/dwojcik/HF-to-GGUF_converter/qwen.cpp/qwen_cpp/convert.py", line 256, in main
    convert(f, args.model_name_or_path, dtype=args.type)
  File "/home/dwojcik/HF-to-GGUF_converter/qwen.cpp/qwen_cpp/convert.py", line 230, in convert
    QwenConverter.convert(f, model, tokenizer, ggml_type)
  File "/home/dwojcik/HF-to-GGUF_converter/qwen.cpp/qwen_cpp/convert.py", line 182, in convert
    cls.dump_config(f, model.config, model.generation_config, tokenizer, ggml_type)
  File "/home/dwojcik/HF-to-GGUF_converter/qwen.cpp/qwen_cpp/convert.py", line 195, in dump_config
    config.seq_length,
  File "/home/dwojcik/.local/lib/python3.10/site-packages/transformers/configuration_utils.py", line 263, in __getattribute__
    return super().__getattribute__(key)
AttributeError: 'Qwen2MoeConfig' object has no attribute 'seq_length'. Did you mean: 'max_length'?

[zhangfan-algo]

我也遇到了 貌似不太支持 求解