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

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  },20  "initializer_range": 0.02,21  "intermediate_size": 11008,22  "label2id": {23    "LABEL_0": 0,24    "LABEL_1": 1,25    "LABEL_2": 2,26    "LABEL_3": 3,27    "LABEL_4": 428  },29  "max_position_embeddings": 16384,30  "mlp_bias": false,31  "model_type": "llama",32  "num_attention_heads": 32,33  "num_hidden_layers": 32,34  "num_key_value_heads": 32,35  "pad_token_id": 2,36  "pretraining_tp": 1,37  "problem_type": "multi_label_classification",38  "rms_norm_eps": 1e-05,39  "rope_scaling": null,40  "rope_theta": 1000000,41  "tie_word_embeddings": false,42  "torch_dtype": "bfloat16",43  "transformers_version": "4.48.3",44  "use_cache": true,45  "vocab_size": 3201646}47