| { | |
| "_name_or_path": "JackFram/llama-160m", | |
| "architectures": [ | |
| "LlamaForSequenceClassification" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "finetuning_task": "qnli", | |
| "hidden_act": "silu", | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "entailment", | |
| "1": "not_entailment" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "entailment": 0, | |
| "not_entailment": 1 | |
| }, | |
| "max_position_embeddings": 2048, | |
| "model_type": "llama", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "num_key_value_heads": 12, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "problem_type": "single_label_classification", | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.31.0", | |
| "use_cache": true, | |
| "vocab_size": 32000 | |
| } | |