bp03/Classification_SST2_Llama_3.2_1B_Model

1{2  "_name_or_path": "meta-llama/Llama-3.2-1B",3  "architectures": [4    "LlamaForSequenceClassification"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 128000,9  "eos_token_id": 128001,10  "head_dim": 64,11  "hidden_act": "silu",12  "hidden_size": 2048,13  "initializer_range": 0.02,14  "intermediate_size": 8192,15  "max_position_embeddings": 131072,16  "mlp_bias": false,17  "model_type": "llama",18  "num_attention_heads": 32,19  "num_hidden_layers": 16,20  "num_key_value_heads": 8,21  "pad_token_id": 128001,22  "pretraining_tp": 1,23  "problem_type": "single_label_classification",24  "rms_norm_eps": 1e-05,25  "rope_scaling": {26    "factor": 32.0,27    "high_freq_factor": 4.0,28    "low_freq_factor": 1.0,29    "original_max_position_embeddings": 8192,30    "rope_type": "llama3"31  },32  "rope_theta": 500000.0,33  "tie_word_embeddings": true,34  "torch_dtype": "float32",35  "transformers_version": "4.45.1",36  "use_cache": true,37  "vocab_size": 12825638}39