Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

TheBloke
/
koala-7B-GPTQ

Text Generation
Transformers
Safetensors
llama
text-generation-inference
4-bit precision
gptq
Model card Files Files and versions Community
6
koala-7B-GPTQ
Ctrl+K
Ctrl+K
  • 2 contributors
History: 26 commits
TheBloke's picture
TheBloke
Update special_tokens_map.json to match other models, like Vicuna - the Koala conversion process does not fill out this file, but based on the code I think these special tokens should be defined.
21e4ac4 over 2 years ago
  • .gitattributes
    1.48 kB
    initial commit over 2 years ago
  • README.md
    6.99 kB
    Update README.md over 2 years ago
  • config.json
    507 Bytes
    Add JSON files over 2 years ago
  • generation_config.json
    137 Bytes
    Add JSON files over 2 years ago
  • koala-7B-4bit-128g.no-act-order.ooba.pt

    Detected Pickle imports (5)

    • "torch.FloatStorage",
    • "torch.HalfStorage",
    • "collections.OrderedDict",
    • "torch.IntStorage",
    • "torch._utils._rebuild_tensor_v2"

    What is a pickle import?

    4 GB
    LFS
    Add model made with oobabooga's older fork of GPTQ, suitable for use in text-generation-webui without requiring an update to GPTQ code. Also for GGML conversion. over 2 years ago
  • koala-7B-4bit-128g.safetensors
    3.89 GB
    LFS
    add safetensors model over 2 years ago
  • params.json
    101 Bytes
    Add JSON files over 2 years ago
  • special_tokens_map.json
    410 Bytes
    Update special_tokens_map.json to match other models, like Vicuna - the Koala conversion process does not fill out this file, but based on the code I think these special tokens should be defined. over 2 years ago
  • tokenizer.model
    500 kB
    LFS
    Add JSON files over 2 years ago
  • tokenizer_config.json
    141 Bytes
    Add JSON files over 2 years ago