torchao-testing/opt-125m-Float8DynamicActivationFloat8WeightConfig-v1-0.13.dev
019
1{2 "_remove_final_layer_norm": false,3 "activation_dropout": 0.0,4 "activation_function": "relu",5 "architectures": [6 "OPTForCausalLM"7 ],8 "attention_dropout": 0.0,9 "bos_token_id": 2,10 "do_layer_norm_before": true,11 "dropout": 0.1,12 "enable_bias": true,13 "eos_token_id": 2,14 "ffn_dim": 3072,15 "hidden_size": 768,16 "init_std": 0.02,17 "layer_norm_elementwise_affine": true,18 "layerdrop": 0.0,19 "max_position_embeddings": 2048,20 "model_type": "opt",21 "num_attention_heads": 12,22 "num_hidden_layers": 12,23 "pad_token_id": 1,24 "prefix": "</s>",25 "quantization_config": {26 "include_input_output_embeddings": false,27 "modules_to_not_convert": null,28 "quant_method": "torchao",29 "quant_type": {30 "default": {31 "_data": {32 "activation_dtype": {33 "_data": "float8_e4m3fn",34 "_type": "torch.dtype"35 },36 "activation_value_lb": null,37 "activation_value_ub": null,38 "granularity": [39 {40 "_data": {},41 "_type": "PerRow",42 "_version": 143 },44 {45 "_data": {},46 "_type": "PerRow",47 "_version": 148 }49 ],50 "kernel_preference": {51 "_data": "AUTO",52 "_type": "KernelPreference"53 },54 "mm_config": {55 "_data": {56 "emulate": false,57 "pad_inner_dim": false,58 "use_fast_accum": true59 },60 "_type": "Float8MMConfig",61 "_version": 162 },63 "set_inductor_config": true,64 "weight_dtype": {65 "_data": "float8_e4m3fn",66 "_type": "torch.dtype"67 }68 },69 "_type": "Float8DynamicActivationFloat8WeightConfig",70 "_version": 171 }72 },73 "quant_type_kwargs": {},74 "untie_embedding_weights": false75 },76 "torch_dtype": "bfloat16",77 "transformers_version": "4.55.2",78 "use_cache": true,79 "vocab_size": 50272,80 "word_embed_proj_dim": 76881}82