{ "_name_or_path": "/covalent/.cache/models/tmp0fx1cfd0wlfe3p3v", "_num_labels": 3, "activation_dropout": 0.0, "activation_function": "gelu", "add_bias_logits": false, "add_final_layer_norm": true, "architectures": [ "MBartForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 0, "classif_dropout": 0.0, "classifier_dropout": 0.0, "d_model": 1024, "decoder_attention_heads": 16, "decoder_ffn_dim": 4096, "decoder_layerdrop": 0.0, "decoder_layers": 12, "decoder_start_token_id": 2, "dropout": 0.1, "early_stopping": null, "encoder_attention_heads": 16, "encoder_ffn_dim": 4096, "encoder_layerdrop": 0.0, "encoder_layers": 12, "eos_token_id": 2, "forced_eos_token_id": 2, "gradient_checkpointing": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "init_std": 0.02, "is_decoder": true, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "max_length": null, "max_position_embeddings": 1024, "model_type": "mbart", "normalize_before": true, "normalize_embedding": true, "num_beams": null, "num_hidden_layers": 12, "output_past": true, "pad_token_id": 1, "quantization_config": { "_load_in_4bit": false, "_load_in_8bit": true, "bnb_4bit_compute_dtype": "bfloat16", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "fp4", "bnb_4bit_use_double_quant": false, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": [ "lm_head" ], "llm_int8_threshold": 6.0, "load_in_4bit": false, "load_in_8bit": true, "quant_method": "bitsandbytes" }, "scale_embedding": true, "static_position_embeddings": false, "tokenizer_class": "MBart50Tokenizer", "torch_dtype": "float16", "transformers_version": "4.46.2", "use_cache": true, "vocab_size": 250054, "api_key": null }