| { | |
| "_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, | |
| "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": { | |
| "activation_dtype": { | |
| "_data": "float8_e4m3fn", | |
| "_type": "torch.dtype" | |
| }, | |
| "activation_value_lb": null, | |
| "activation_value_ub": null, | |
| "general_kernel_preference": { | |
| "_data": "DEFAULT", | |
| "_type": "GeneralKernelPreference" | |
| }, | |
| "granularity": [ | |
| { | |
| "_data": {}, | |
| "_type": "PerRow", | |
| "_version": 1 | |
| }, | |
| { | |
| "_data": {}, | |
| "_type": "PerRow", | |
| "_version": 1 | |
| } | |
| ], | |
| "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": 1 | |
| } | |
| }, | |
| "quant_type_kwargs": {}, | |
| "untie_embedding_weights": false | |
| }, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.53.3", | |
| "use_cache": true, | |
| "vocab_size": 50272, | |
| "word_embed_proj_dim": 768 | |
| } | |