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

  • Log In
  • Sign Up

TheBloke
/
Upstage-Llama-2-70B-instruct-v2-GPTQ

Text Generation
Transformers
Safetensors
English
llama
upstage
llama-2
instruct
instruction
text-generation-inference
4-bit precision
gptq
Model card Files Files and versions Community
3
Upstage-Llama-2-70B-instruct-v2-GPTQ
35.3 GB
  • 2 contributors
History: 22 commits
TheBloke's picture
TheBloke
jeffbiocode's picture
jeffbiocode
Add a system message so the example code works (#3)
8859ee1 almost 2 years ago
  • .gitattributes
    1.52 kB
    initial commit about 2 years ago
  • LICENSE.txt
    7.02 kB
    Initial GPTQ model commit about 2 years ago
  • Notice
    112 Bytes
    Initial GPTQ model commit about 2 years ago
  • README.md
    21.4 kB
    Add a system message so the example code works (#3) almost 2 years ago
  • USE_POLICY.md
    4.77 kB
    Initial GPTQ model commit about 2 years ago
  • config.json
    891 Bytes
    Update for Transformers GPTQ support about 2 years ago
  • generation_config.json
    162 Bytes
    Initial GPTQ model commit about 2 years ago
  • model.safetensors
    35.3 GB
    LFS
    Update for Transformers GPTQ support about 2 years ago
  • quantize_config.json
    185 Bytes
    Update for Transformers GPTQ support about 2 years ago
  • tokenizer.json
    1.84 MB
    Initial GPTQ model commit about 2 years ago
  • tokenizer.model
    500 kB
    LFS
    Initial GPTQ model commit about 2 years ago
  • tokenizer_config.json
    749 Bytes
    Initial GPTQ model commit about 2 years ago