| { | |
| "_name_or_path": "bigbird-pegasus-large-K-booksum", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "BigBirdPegasusForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attention_type": "block_sparse", | |
| "block_size": 64, | |
| "bos_token_id": 2, | |
| "classifier_dropout": 0.0, | |
| "d_model": 1024, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 4096, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 16, | |
| "decoder_start_token_id": 2, | |
| "dropout": 0.1, | |
| "early_stopping": true, | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 16, | |
| "eos_token_id": 1, | |
| "gradient_checkpointing": false, | |
| "init_std": 0.02, | |
| "is_decoder": true, | |
| "is_encoder_decoder": false, | |
| "length_penalty": 3.5, | |
| "max_length": 512, | |
| "max_position_embeddings": 4096, | |
| "min_length": 32, | |
| "model_type": "bigbird_pegasus", | |
| "no_repeat_ngram_size": 3, | |
| "num_beams": 5, | |
| "num_hidden_layers": 16, | |
| "num_random_blocks": 3, | |
| "pad_token_id": 0, | |
| "quantization_config": { | |
| "_load_in_4bit": false, | |
| "_load_in_8bit": true, | |
| "bnb_4bit_compute_dtype": "float32", | |
| "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": null, | |
| "llm_int8_threshold": 6.0, | |
| "load_in_4bit": false, | |
| "load_in_8bit": true, | |
| "quant_method": "bitsandbytes" | |
| }, | |
| "scale_embedding": true, | |
| "tokenizer_class": "PegasusTokenizer", | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.40.2", | |
| "use_bias": false, | |
| "use_cache": false, | |
| "vocab_size": 96103 | |
| } | |