Issues of converting safetensors to gguf with convert.py

[592319702]

I want to convert safetensors to gguf with convert.py
But I hit the issue as follow,
(mlx) I542464@DY4GPKX1J0 llama.cpp % python convert.py ../mlx-examples/lora/lora_fused_model/My-Mistral-7B-fine-tuned Loading model file ../mlx-examples/lora/lora_fused_model/My-Mistral-7B-fine-tuned/model-00001-of-00003.safetensors Loading model file ../mlx-examples/lora/lora_fused_model/My-Mistral-7B-fine-tuned/model-00001-of-00003.safetensors Loading model file ../mlx-examples/lora/lora_fused_model/My-Mistral-7B-fine-tuned/model-00002-of-00003.safetensors Loading model file ../mlx-examples/lora/lora_fused_model/My-Mistral-7B-fine-tuned/model-00003-of-00003.safetensors params = Params(n_vocab=32000, n_embd=4096, n_layer=32, n_ctx=32768, n_ff=14336, n_head=32, n_head_kv=8, n_experts=None, n_experts_used=None, f_norm_eps=1e-05, rope_scaling_type=None, f_rope_freq_base=10000.0, f_rope_scale=None, n_orig_ctx=None, rope_finetuned=None, ftype=None, path_model=PosixPath('../mlx-examples/lora/lora_fused_model/My-Mistral-7B-fine-tuned')) Found vocab files: {'tokenizer.model': None, 'vocab.json': None, 'tokenizer.json': PosixPath('../mlx-examples/lora/lora_fused_model/My-Mistral-7B-fine-tuned/tokenizer.json')} Loading vocab file '../mlx-examples/lora/lora_fused_model/My-Mistral-7B-fine-tuned/tokenizer.json', type 'spm' Traceback (most recent call last): File "/Users/I542464/mlx-test/llama.cpp/convert.py", line 1474, in <module> main() File "/Users/I542464/mlx-test/llama.cpp/convert.py", line 1442, in main vocab, special_vocab = vocab_factory.load_vocab(args.vocab_type, model_parent_path) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/I542464/mlx-test/llama.cpp/convert.py", line 1328, in load_vocab vocab = SentencePieceVocab( ^^^^^^^^^^^^^^^^^^^ File "/Users/I542464/mlx-test/llama.cpp/convert.py", line 394, in __init__ self.sentencepiece_tokenizer = SentencePieceProcessor(str(fname_tokenizer)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/I542464/miniconda3/envs/mlx/lib/python3.11/site-packages/sentencepiece/__init__.py", line 447, in Init self.Load(model_file=model_file, model_proto=model_proto) File "/Users/I542464/miniconda3/envs/mlx/lib/python3.11/site-packages/sentencepiece/__init__.py", line 905, in Load return self.LoadFromFile(model_file) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/I542464/miniconda3/envs/mlx/lib/python3.11/site-packages/sentencepiece/__init__.py", line 310, in LoadFromFile return _sentencepiece.SentencePieceProcessor_LoadFromFile(self, arg) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: Internal: /Users/runner/work/sentencepiece/sentencepiece/src/sentencepiece_processor.cc(1102) [model_proto->ParseFromArray(serialized.data(), serialized.size())]

My model files is as follow,
config.json model-00002-of-00003.safetensors special_tokens_map.json tokenizer_config.json model-00001-of-00003.safetensors model-00003-of-00003.safetensors tokenizer.json

[Artefact2]

convert.py --vocab-type hfft

[github-actions]

This issue is stale because it has been open for 30 days with no activity.

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.