Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: ModelCloud/GPTQModel
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: v0.9.3
Choose a base ref
...
head repository: ModelCloud/GPTQModel
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: v0.9.4
Choose a head ref
  • 12 commits
  • 41 files changed
  • 7 contributors

Commits on Jul 3, 2024

  1. unit test use tinyllama-15M model (#143)

    * unit test use tinyllama-15M model
    
    * load dataset with range 2048
    
    * change load_dataset, download model to local and modify config.json
    
    * modify model path
    
    * Update test_perplexity.py
    
    * Update test_perplexity.py
    
    ---------
    
    Co-authored-by: Qubitium-ModelCloud <[email protected]>
    ZYC-ModelCloud and Qubitium authored Jul 3, 2024
    Configuration menu
    Copy the full SHA
    8ae2645 View commit details
    Browse the repository at this point in the history
  2. Configuration menu
    Copy the full SHA
    2ace901 View commit details
    Browse the repository at this point in the history
  3. Update ip (#153)

    CSY-ModelCloud authored Jul 3, 2024
    Configuration menu
    Copy the full SHA
    65f572a View commit details
    Browse the repository at this point in the history
  4. Update README.md (#154)

    Qubitium authored Jul 3, 2024
    Configuration menu
    Copy the full SHA
    1a7f097 View commit details
    Browse the repository at this point in the history
  5. Update README.md (#155)

    Qubitium authored Jul 3, 2024
    Configuration menu
    Copy the full SHA
    2e09c4f View commit details
    Browse the repository at this point in the history
  6. Configuration menu
    Copy the full SHA
    514e6c5 View commit details
    Browse the repository at this point in the history
  7. [FEATURE] Add Transformers Integration (#147)

    * add transformers integration
    
    * use gptqmodel
    
    * Update hf_quantizer_gptq.py
    
    * add monkey_patch_gptq_transformers()
    
    * cleanup
    
    * Fix issue: incorrect qlinear in transformers inegration quantization model
    
    * add unit tests of Transformers integration
    
    * monkey patch model.save_pretrained()
    
    * cleanup
    
    * cleanup
    
    * rename monkey_patch_gptq_transformers() to monkey_patch_gptqmodel_into_transformers()
    
    * select_quant_linear() remove "disable_exllama" param
    
    ---------
    
    Co-authored-by: Qubitium-ModelCloud <[email protected]>
    ZX-ModelCloud and Qubitium authored Jul 3, 2024
    Configuration menu
    Copy the full SHA
    76b7fc9 View commit details
    Browse the repository at this point in the history
  8. Configuration menu
    Copy the full SHA
    4115579 View commit details
    Browse the repository at this point in the history

Commits on Jul 4, 2024

  1. fix typo gamma2 -> gemma2 (#158)

    Co-authored-by: LRL-ModelCloud <[email protected]>
    LRL-ModelCloud and LRL2-ModelCloud authored Jul 4, 2024
    Configuration menu
    Copy the full SHA
    966ecb3 View commit details
    Browse the repository at this point in the history
  2. Configuration menu
    Copy the full SHA
    183f37e View commit details
    Browse the repository at this point in the history
  3. Configuration menu
    Copy the full SHA
    9a394f8 View commit details
    Browse the repository at this point in the history
  4. Update version.py (#162)

    Qubitium authored Jul 4, 2024
    Configuration menu
    Copy the full SHA
    527cffb View commit details
    Browse the repository at this point in the history
Loading