randaller / llama-chat

Chat with Meta's LLaMA models at home made easy
GNU General Public License v3.0
834 stars 118 forks source link

merge-weights.py fails merging the 13B model #8

Closed teknoraver closed 1 year ago

teknoraver commented 1 year ago
matteo@llama:~/llama-chat$ python3 merge-weights.py --input_dir ../LLaMA --model_size 13B
Traceback (most recent call last):
  File "merge-weights.py", line 168, in <module>
    main()
  File "merge-weights.py", line 163, in main
    model_size=args.model_size,
  File "merge-weights.py", line 95, in write_model
    f"layers.{layer_i}.ffn_norm.weight": loaded[0][f"layers.{layer_i}.ffn_norm.weight"],
TypeError: unsupported operand type(s) for |=: 'dict' and 'dict'
teknoraver commented 1 year ago

happens with 30B too

randaller commented 1 year ago

@teknoraver Use python version 3.9+

randaller commented 1 year ago

Duplicate of #4