Quantized_CL

Model Card for hnpinq/Quantized_CL

This model was created using the pruna library. Pruna is a model optimization framework built for developers, enabling you to deliver more efficient models with minimal implementation overhead.

Usage

First things first, you need to install the pruna library:

pip install pruna

You can use the None library to load the model but this might not include all optimizations by default.

To ensure that all optimizations are applied, use the pruna library to load the model using the following code:

from pruna import PrunaModel

loaded_model = PrunaModel.from_hub(
    "hnpinq/Quantized_CL"
)

After loading the model, you can use the inference methods of the original model. Take a look at the documentation for more usage information.

Smash Configuration

The compression configuration of the model is stored in the smash_config.json file, which describes the optimization methods that were applied to the model.

{
    "batcher": null,
    "cacher": null,
    "compiler": "torch_compile",
    "factorizer": null,
    "pruner": null,
    "quantizer": "hqq_diffusers",
    "hqq_diffusers_backend": "torchao_int4",
    "hqq_diffusers_group_size": 64,
    "hqq_diffusers_weight_bits": 8,
    "torch_compile_backend": "inductor",
    "torch_compile_dynamic": null,
    "torch_compile_fullgraph": true,
    "torch_compile_make_portable": false,
    "torch_compile_max_kv_cache_size": 400,
    "torch_compile_mode": "max-autotune",
    "torch_compile_seqlen_manual_cuda_graph": 100,
    "torch_compile_target": "model",
    "batch_size": 1,
    "device": "cuda",
    "save_fns": [
        "hqq_diffusers",
        "save_before_apply"
    ],
    "load_fns": [
        "hqq_diffusers"
    ],
    "reapply_after_load": {
        "factorizer": null,
        "pruner": null,
        "quantizer": null,
        "cacher": null,
        "compiler": "torch_compile",
        "batcher": null
    }
}

🌍 Join the Pruna AI community!