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

  • Log In
  • Sign Up

Spaces:
aletrn
/
lisa-on-cuda
Paused

App Files Files Community
1
Fetching metadata from the HF Docker repository...
lisa-on-cuda / model /llava /model
Ctrl+K
Ctrl+K
  • 15 contributors
History: 2 commits
x-lai
support 4bit and 8bit inference
968fffb almost 2 years ago
  • mpt
    Inference code and model LISA-13B-llama2-v0 are released almost 2 years ago
  • __init__.py
    113 Bytes
    Inference code and model LISA-13B-llama2-v0 are released almost 2 years ago
  • apply_delta.py
    1.96 kB
    Inference code and model LISA-13B-llama2-v0 are released almost 2 years ago
  • consolidate.py
    898 Bytes
    Inference code and model LISA-13B-llama2-v0 are released almost 2 years ago
  • llava.py
    16.9 kB
    support 4bit and 8bit inference almost 2 years ago
  • llava_mpt.py
    16.7 kB
    Inference code and model LISA-13B-llama2-v0 are released almost 2 years ago
  • make_delta.py
    2.26 kB
    Inference code and model LISA-13B-llama2-v0 are released almost 2 years ago
  • utils.py
    3.16 kB
    Inference code and model LISA-13B-llama2-v0 are released almost 2 years ago