jerryzh168's picture
Upload OPTForCausalLM
4820374 verified
{
"_remove_final_layer_norm": false,
"activation_dropout": 0.0,
"activation_function": "relu",
"architectures": [
"OPTForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 2,
"do_layer_norm_before": true,
"dropout": 0.1,
"dtype": "bfloat16",
"enable_bias": true,
"eos_token_id": 2,
"ffn_dim": 3072,
"hidden_size": 768,
"init_std": 0.02,
"layer_norm_elementwise_affine": true,
"layerdrop": 0.0,
"max_position_embeddings": 2048,
"model_type": "opt",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 1,
"prefix": "</s>",
"quantization_config": {
"include_input_output_embeddings": false,
"modules_to_not_convert": null,
"quant_method": "torchao",
"quant_type": {
"default": {
"_data": {
"module_fqn_to_config": {
"_default": {
"_data": {
"granularity": {
"_data": {
"axis": 0
},
"_type": "PerAxis",
"_version": 1
},
"intx_packing_format": {
"_data": "UNPACKED_TO_INT8",
"_type": "IntxPackingFormat"
},
"layout": {
"_data": {},
"_type": "QDQLayout",
"_version": 1
},
"mapping_type": {
"_data": "SYMMETRIC",
"_type": "MappingType"
},
"scale_dtype": null,
"weight_dtype": {
"_data": "int8",
"_type": "torch.dtype"
}
},
"_type": "IntxWeightOnlyConfig",
"_version": 2
},
"model.decoder.layers.3.self_attn.k_proj": {
"_data": {
"group_size": 128,
"int4_choose_qparams_algorithm": {
"_data": "TINYGEMM",
"_type": "Int4ChooseQParamsAlgorithm"
},
"int4_packing_format": "tile_packed_to_4d",
"layout": {
"_data": {
"inner_k_tiles": 8
},
"_type": "TensorCoreTiledLayout",
"_version": 1
},
"preserve_zero": null,
"set_inductor_config": true,
"use_hqq": false,
"zero_point_domain": {
"_data": "NONE",
"_type": "ZeroPointDomain"
}
},
"_type": "Int4WeightOnlyConfig",
"_version": 2
},
"model.decoder.layers.3.self_attn.q_proj": {
"_data": {
"group_size": 128,
"int4_choose_qparams_algorithm": {
"_data": "TINYGEMM",
"_type": "Int4ChooseQParamsAlgorithm"
},
"int4_packing_format": "tile_packed_to_4d",
"layout": {
"_data": {
"inner_k_tiles": 8
},
"_type": "TensorCoreTiledLayout",
"_version": 1
},
"preserve_zero": null,
"set_inductor_config": true,
"use_hqq": false,
"zero_point_domain": {
"_data": "NONE",
"_type": "ZeroPointDomain"
}
},
"_type": "Int4WeightOnlyConfig",
"_version": 2
},
"model.decoder.layers.3.self_attn.qkv_proj": {
"_data": {
"group_size": 128,
"int4_choose_qparams_algorithm": {
"_data": "TINYGEMM",
"_type": "Int4ChooseQParamsAlgorithm"
},
"int4_packing_format": "tile_packed_to_4d",
"layout": {
"_data": {
"inner_k_tiles": 8
},
"_type": "TensorCoreTiledLayout",
"_version": 1
},
"preserve_zero": null,
"set_inductor_config": true,
"use_hqq": false,
"zero_point_domain": {
"_data": "NONE",
"_type": "ZeroPointDomain"
}
},
"_type": "Int4WeightOnlyConfig",
"_version": 2
},
"model.decoder.layers.3.self_attn.v_proj": {
"_data": {
"group_size": 128,
"int4_choose_qparams_algorithm": {
"_data": "TINYGEMM",
"_type": "Int4ChooseQParamsAlgorithm"
},
"int4_packing_format": "tile_packed_to_4d",
"layout": {
"_data": {
"inner_k_tiles": 8
},
"_type": "TensorCoreTiledLayout",
"_version": 1
},
"preserve_zero": null,
"set_inductor_config": true,
"use_hqq": false,
"zero_point_domain": {
"_data": "NONE",
"_type": "ZeroPointDomain"
}
},
"_type": "Int4WeightOnlyConfig",
"_version": 2
},
"re:model\\.decoder\\.layers\\..+\\.self_attn\\.k_proj": {
"_data": {
"activation_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
},
"activation_value_lb": null,
"activation_value_ub": null,
"granularity": [
{
"_data": {},
"_type": "PerRow",
"_version": 1
},
{
"_data": {},
"_type": "PerRow",
"_version": 1
}
],
"kernel_preference": {
"_data": "AUTO",
"_type": "KernelPreference"
},
"mm_config": {
"_data": {
"emulate": false,
"pad_inner_dim": false,
"use_fast_accum": true
},
"_type": "Float8MMConfig",
"_version": 1
},
"set_inductor_config": true,
"weight_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
}
},
"_type": "Float8DynamicActivationFloat8WeightConfig",
"_version": 2
},
"re:model\\.decoder\\.layers\\..+\\.self_attn\\.out_pro": {
"_data": {
"activation_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
},
"activation_value_lb": null,
"activation_value_ub": null,
"granularity": [
{
"_data": {},
"_type": "PerRow",
"_version": 1
},
{
"_data": {},
"_type": "PerRow",
"_version": 1
}
],
"kernel_preference": {
"_data": "AUTO",
"_type": "KernelPreference"
},
"mm_config": {
"_data": {
"emulate": false,
"pad_inner_dim": false,
"use_fast_accum": true
},
"_type": "Float8MMConfig",
"_version": 1
},
"set_inductor_config": true,
"weight_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
}
},
"_type": "Float8DynamicActivationFloat8WeightConfig",
"_version": 2
},
"re:model\\.decoder\\.layers\\..+\\.self_attn\\.q_proj": {
"_data": {
"activation_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
},
"activation_value_lb": null,
"activation_value_ub": null,
"granularity": [
{
"_data": {},
"_type": "PerRow",
"_version": 1
},
{
"_data": {},
"_type": "PerRow",
"_version": 1
}
],
"kernel_preference": {
"_data": "AUTO",
"_type": "KernelPreference"
},
"mm_config": {
"_data": {
"emulate": false,
"pad_inner_dim": false,
"use_fast_accum": true
},
"_type": "Float8MMConfig",
"_version": 1
},
"set_inductor_config": true,
"weight_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
}
},
"_type": "Float8DynamicActivationFloat8WeightConfig",
"_version": 2
},
"re:model\\.decoder\\.layers\\..+\\.self_attn\\.qkv_proj": {
"_data": {
"activation_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
},
"activation_value_lb": null,
"activation_value_ub": null,
"granularity": [
{
"_data": {},
"_type": "PerRow",
"_version": 1
},
{
"_data": {},
"_type": "PerRow",
"_version": 1
}
],
"kernel_preference": {
"_data": "AUTO",
"_type": "KernelPreference"
},
"mm_config": {
"_data": {
"emulate": false,
"pad_inner_dim": false,
"use_fast_accum": true
},
"_type": "Float8MMConfig",
"_version": 1
},
"set_inductor_config": true,
"weight_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
}
},
"_type": "Float8DynamicActivationFloat8WeightConfig",
"_version": 2
},
"re:model\\.decoder\\.layers\\..+\\.self_attn\\.v_proj": {
"_data": {
"activation_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
},
"activation_value_lb": null,
"activation_value_ub": null,
"granularity": [
{
"_data": {},
"_type": "PerRow",
"_version": 1
},
{
"_data": {},
"_type": "PerRow",
"_version": 1
}
],
"kernel_preference": {
"_data": "AUTO",
"_type": "KernelPreference"
},
"mm_config": {
"_data": {
"emulate": false,
"pad_inner_dim": false,
"use_fast_accum": true
},
"_type": "Float8MMConfig",
"_version": 1
},
"set_inductor_config": true,
"weight_dtype": {
"_data": "float8_e4m3fn",
"_type": "torch.dtype"
}
},
"_type": "Float8DynamicActivationFloat8WeightConfig",
"_version": 2
}
}
},
"_type": "ModuleFqnToConfig",
"_version": 1
}
},
"quant_type_kwargs": {},
"untie_embedding_weights": false
},
"transformers_version": "4.57.0.dev0",
"use_cache": true,
"vocab_size": 50272,
"word_embed_proj_dim": 768
}