SupraLabs

/

Supra-Mini-v4-2M

like 8

Follow

SupraLabs 193

INFO:hf-to-gguf:Loading model: tempmodel
INFO:hf-to-gguf:Model architecture: LlamaForCausalLM
INFO:hf-to-gguf:gguf: indexing model part 'model.safetensors'
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:token_embd.weight,          torch.float32 --> Q8_0, shape = {64, 4096}
INFO:hf-to-gguf:blk.0.attn_norm.weight,     torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:blk.0.ffn_down.weight,      torch.float32 --> Q8_0, shape = {128, 64}
INFO:hf-to-gguf:blk.0.ffn_gate.weight,      torch.float32 --> Q8_0, shape = {64, 128}
INFO:hf-to-gguf:blk.0.ffn_up.weight,        torch.float32 --> Q8_0, shape = {64, 128}
INFO:hf-to-gguf:blk.0.ffn_norm.weight,      torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:blk.0.attn_k.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.0.attn_output.weight,   torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.0.attn_q.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.0.attn_v.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.1.attn_norm.weight,     torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:blk.1.ffn_down.weight,      torch.float32 --> Q8_0, shape = {128, 64}
INFO:hf-to-gguf:blk.1.ffn_gate.weight,      torch.float32 --> Q8_0, shape = {64, 128}
INFO:hf-to-gguf:blk.1.ffn_up.weight,        torch.float32 --> Q8_0, shape = {64, 128}
INFO:hf-to-gguf:blk.1.ffn_norm.weight,      torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:blk.1.attn_k.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.1.attn_output.weight,   torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.1.attn_q.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.1.attn_v.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.2.attn_norm.weight,     torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:blk.2.ffn_down.weight,      torch.float32 --> Q8_0, shape = {128, 64}
INFO:hf-to-gguf:blk.2.ffn_gate.weight,      torch.float32 --> Q8_0, shape = {64, 128}
INFO:hf-to-gguf:blk.2.ffn_up.weight,        torch.float32 --> Q8_0, shape = {64, 128}
INFO:hf-to-gguf:blk.2.ffn_norm.weight,      torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:blk.2.attn_k.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.2.attn_output.weight,   torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.2.attn_q.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.2.attn_v.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.3.attn_norm.weight,     torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:blk.3.ffn_down.weight,      torch.float32 --> Q8_0, shape = {128, 64}
INFO:hf-to-gguf:blk.3.ffn_gate.weight,      torch.float32 --> Q8_0, shape = {64, 128}
INFO:hf-to-gguf:blk.3.ffn_up.weight,        torch.float32 --> Q8_0, shape = {64, 128}
INFO:hf-to-gguf:blk.3.ffn_norm.weight,      torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:blk.3.attn_k.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.3.attn_output.weight,   torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.3.attn_q.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.3.attn_v.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.4.attn_norm.weight,     torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:blk.4.ffn_down.weight,      torch.float32 --> Q8_0, shape = {128, 64}
INFO:hf-to-gguf:blk.4.ffn_gate.weight,      torch.float32 --> Q8_0, shape = {64, 128}
INFO:hf-to-gguf:blk.4.ffn_up.weight,        torch.float32 --> Q8_0, shape = {64, 128}
INFO:hf-to-gguf:blk.4.ffn_norm.weight,      torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:blk.4.attn_k.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.4.attn_output.weight,   torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.4.attn_q.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:blk.4.attn_v.weight,        torch.float32 --> Q8_0, shape = {64, 64}
INFO:hf-to-gguf:output_norm.weight,         torch.float32 --> F32, shape = {64}
INFO:hf-to-gguf:Set meta model
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:gguf: context length = 512
INFO:hf-to-gguf:gguf: embedding length = 64
INFO:hf-to-gguf:gguf: feed forward length = 128
INFO:hf-to-gguf:gguf: head count = 8
INFO:hf-to-gguf:gguf: key-value head count = 8
WARNING:hf-to-gguf:Unknown RoPE type: default
INFO:hf-to-gguf:gguf: rope scaling type = NONE
INFO:hf-to-gguf:gguf: rope theta = 10000.0
INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06
INFO:hf-to-gguf:gguf: file type = 7
INFO:hf-to-gguf:Set model quantization version
INFO:hf-to-gguf:Set model tokenizer
Traceback (most recent call last):
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/conversion/llama.py", line 55, in set_vocab
    self._set_vocab_sentencepiece()
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/conversion/base.py", line 1664, in _set_vocab_sentencepiece
    tokens, scores, toktypes = self._create_vocab_sentencepiece()
                               ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/conversion/base.py", line 1681, in _create_vocab_sentencepiece
    raise FileNotFoundError(f"File not found: {tokenizer_path}")
FileNotFoundError: File not found: tempmodel/tokenizer.model

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/conversion/llama.py", line 58, in set_vocab
    self._set_vocab_llama_hf()
    ~~~~~~~~~~~~~~~~~~~~~~~~^^
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/conversion/base.py", line 1766, in _set_vocab_llama_hf
    vocab = gguf.LlamaHfVocab(self.dir_model)
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/gguf-py/gguf/vocab.py", line 529, in __init__
    raise FileNotFoundError('Cannot find Llama BPE tokenizer')
FileNotFoundError: Cannot find Llama BPE tokenizer

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/convert_hf_to_gguf.py", line 260, in <module>
    main()
    ~~~~^^
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/convert_hf_to_gguf.py", line 254, in main
    model_instance.write()
    ~~~~~~~~~~~~~~~~~~~~^^
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/conversion/base.py", line 942, in write
    self.prepare_metadata(vocab_only=False)
    ~~~~~~~~~~~~~~~~~~~~~^^^^^^^^^^^^^^^^^^
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/conversion/base.py", line 1103, in prepare_metadata
    self.set_vocab()
    ~~~~~~~~~~~~~~^^
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/conversion/llama.py", line 61, in set_vocab
    self._set_vocab_gpt2()
    ~~~~~~~~~~~~~~~~~~~~^^
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/conversion/base.py", line 1598, in _set_vocab_gpt2
    tokens, toktypes, tokpre = self.get_vocab_base()
                               ~~~~~~~~~~~~~~~~~~~^^
  File "/media/sapbot/steam/expirements/quantizing/llama.cpp/conversion/base.py", line 1255, in get_vocab_base
    tokenizer = AutoTokenizer.from_pretrained(self.dir_model)
  File "/media/sapbot/steam/conda/base/lib/python3.13/site-packages/transformers/models/auto/tokenization_auto.py", line 1137, in from_pretrained
    raise ValueError(
        f"Tokenizer class {tokenizer_class_candidate} does not exist or is not currently imported."
    )
ValueError: Tokenizer class TokenizersBackend does not exist or is not currently imported.
Unbundle Objects Error: Failed to decompress input: Could not decompress embedded file contents: Data corruption detected

While quantizing with standart llama.cpp. Tried ANY of SupraLabs's models