{ "_name_or_path": "./awq-tinyllama-1.1b", "architectures": [ "LlamaForSequenceClassification" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3", "4": "LABEL_4", "5": "LABEL_5", "6": "LABEL_6", "7": "LABEL_7", "8": "LABEL_8", "9": "LABEL_9", "10": "LABEL_10" }, "initializer_range": 0.02, "intermediate_size": 5632, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_10": 10, "LABEL_2": 2, "LABEL_3": 3, "LABEL_4": 4, "LABEL_5": 5, "LABEL_6": 6, "LABEL_7": 7, "LABEL_8": 8, "LABEL_9": 9 }, "max_position_embeddings": 2048, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 22, "num_key_value_heads": 4, "pretraining_tp": 1, "quantization_config": { "backend": "autoawq", "bits": 4, "do_fuse": false, "fuse_max_seq_len": null, "group_size": 128, "modules_to_fuse": null, "modules_to_not_convert": null, "quant_method": "awq", "version": "gemm", "zero_point": true }, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.38.2", "use_cache": true, "vocab_size": 32000 }