defog

/

llama-3-sqlcoder-8b

like 188

Follow

Defog.ai 77

I converted it to gguf format from this repo omeryentur/llama-3-sqlcoder-8b-GGUF. you can use you can do it yourself. I leave the colab notebook here. https://colab.research.google.com/drive/1P646NEg33BZy4BfLDNpTz0V0lwIU3CHu

@omeryenturfor thanks for the answer!!

Im using the link --> https://colab.research.google.com/drive/1P646NEg33BZy4BfLDNpTz0V0lwIU3CHu , but im still having the tokenizer issue:
Traceback (most recent call last):
File "/content/llama.cpp/convert.py", line 1714, in
main()
File "/content/llama.cpp/convert.py", line 1671, in main
vocab, special_vocab = vocab_factory.load_vocab(vocab_types, model_parent_path)
File "/content/llama.cpp/convert.py", line 1522, in load_vocab
vocab = self._create_vocab_by_path(vocab_types)
File "/content/llama.cpp/convert.py", line 1512, in _create_vocab_by_path
raise FileNotFoundError(f"Could not find a tokenizer matching any of {vocab_types}")
FileNotFoundError: Could not find a tokenizer matching any of ['spm', 'hfft']

May i be doing something wrong?

Thanks so much and regards

change this part of code !python llama.cpp/convert.py {MODEL_NAME} --outtype f16 --outfile {fp16} -> !python llama.cpp/convert.py {MODEL_NAME} --outtype f16 --outfile {fp16} --vocab-type hfft --pad-vocab

@omeryentur thanks so much for the answer.

I have done that but now im getting the error:
Traceback (most recent call last):
File "/content/llama.cpp/convert.py", line 1714, in
main()
File "/content/llama.cpp/convert.py", line 1671, in main
vocab, special_vocab = vocab_factory.load_vocab(vocab_types, model_parent_path)
File "/content/llama.cpp/convert.py", line 1522, in load_vocab
vocab = self._create_vocab_by_path(vocab_types)
File "/content/llama.cpp/convert.py", line 1512, in _create_vocab_by_path
raise FileNotFoundError(f"Could not find a tokenizer matching any of {vocab_types}")
FileNotFoundError: Could not find a tokenizer matching any of ['hfft']

!python llama.cpp/convert.py {MODEL_NAME} --outtype f16 --outfile {fp16} --vocab-type bpe This should work

It is still executing, but it seems that its working.

Thanks so much for the answers @omeryentur .

Regards