Model does *NOT* work.

#1
by ZeroWw - opened
config.json: 100%
 730/730 [00:00<00:00, 23.9kB/s]
merges.txt: 
 1.67M/? [00:00<00:00, 59.0kB/s]
added_tokens.json: 100%
 707/707 [00:00<00:00, 20.7kB/s]
special_tokens_map.json: 100%
 613/613 [00:00<00:00, 18.5kB/s]
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
/tmp/ipython-input-2433247585.py in <cell line: 0>()
      3 model_name = "qihoo360/Light-IF-32B"
      4 
----> 5 tokenizer = AutoTokenizer.from_pretrained(model_name)
      6 model = AutoModelForCausalLM.from_pretrained(
      7     model_name,

4 frames
/usr/local/lib/python3.11/dist-packages/transformers/models/qwen2/tokenization_qwen2.py in __init__(self, vocab_file, merges_file, errors, unk_token, bos_token, eos_token, pad_token, clean_up_tokenization_spaces, split_special_tokens, **kwargs)
    170         )
    171 
--> 172         with open(vocab_file, encoding="utf-8") as vocab_handle:
    173             self.encoder = json.load(vocab_handle)
    174         self.decoder = {v: k for k, v in self.encoder.items()}

TypeError: expected str, bytes or os.PathLike object, not NoneType

also weights are missing.

北京奇虎科技有限公司 org

Thank you for your attention. Due to network issues, the weights were not uploaded successfully. We are re-uploading them and expect to complete the upload today.

I don't have a file to calibrate it with, so no imatrix, but here's the first GGUF of this model, now that it's uploaded. https://huggingface.co/DeProgrammer/Light-IF-32B-Q4_K_M-GGUF

AWQ version is uploaded!

Sign up or log in to comment