sharpenb's picture
87301df3be4656fbfc2ef21f9cd7815b3a932f4e328cf6df166c3a0f5049c236
f8a4e0f verified
raw
history blame
1.02 kB
{
"api_key": null,
"verify_url": "http://johnrachwan.pythonanywhere.com",
"smash_config": {
"pruners": "None",
"pruning_ratio": 0.0,
"factorizers": "None",
"quantizers": "['hqq']",
"weight_quantization_bits": 1,
"output_deviation": 0.005,
"compilers": "None",
"static_batch": true,
"static_shape": true,
"controlnet": "None",
"unet_dim": 4,
"device": "cuda",
"cache_dir": "/ceph/hdd/staff/charpent/.cache/models0hoiwdco",
"batch_size": 1,
"model_name": "NousResearch/Meta-Llama-3-8B",
"task": "text_text_generation",
"max_batch_size": 1,
"qtype_weight": "torch.qint8",
"qtype_activation": "torch.quint8",
"qobserver": "<class 'torch.ao.quantization.observer.MinMaxObserver'>",
"qscheme": "torch.per_tensor_symmetric",
"qconfig": "x86",
"group_size": 128,
"damp_percent": 0.1,
"save_load_fn": "hqq"
}
}