aieng-lab/CodeLlama-7b-hf_comment-type-java

1{2  "_name_or_path": "meta-llama/CodeLlama-7b-hf",3  "architectures": [4    "LlamaForSequenceClassification"5  ],6  "attention_bias": false,7  "attention_dropout": 0.0,8  "bos_token_id": 1,9  "eos_token_id": 2,10  "head_dim": 128,11  "hidden_act": "silu",12  "hidden_size": 4096,13  "id2label": {14    "0": "LABEL_0",15    "1": "LABEL_1",16    "2": "LABEL_2",17    "3": "LABEL_3",18    "4": "LABEL_4",19    "5": "LABEL_5",20    "6": "LABEL_6"21  },22  "initializer_range": 0.02,23  "intermediate_size": 11008,24  "label2id": {25    "LABEL_0": 0,26    "LABEL_1": 1,27    "LABEL_2": 2,28    "LABEL_3": 3,29    "LABEL_4": 4,30    "LABEL_5": 5,31    "LABEL_6": 632  },33  "max_position_embeddings": 16384,34  "mlp_bias": false,35  "model_type": "llama",36  "num_attention_heads": 32,37  "num_hidden_layers": 32,38  "num_key_value_heads": 32,39  "pad_token_id": 2,40  "pretraining_tp": 1,41  "problem_type": "multi_label_classification",42  "rms_norm_eps": 1e-05,43  "rope_scaling": null,44  "rope_theta": 1000000,45  "tie_word_embeddings": false,46  "torch_dtype": "bfloat16",47  "transformers_version": "4.48.3",48  "use_cache": true,49  "vocab_size": 3201650}51