| { |
| "_name_or_path": "ready1", |
| "architectures": [ |
| "LlamaForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100264, |
| "eos_token_id": 100265, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_size": 4608, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1", |
| "2": "LABEL_2", |
| "3": "LABEL_3" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 14336, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_2": 2, |
| "LABEL_3": 3 |
| }, |
| "max_position_embeddings": 131072, |
| "mlp_bias": false, |
| "model_type": "llama", |
| "num_attention_heads": 36, |
| "num_hidden_layers": 26, |
| "num_key_value_heads": 9, |
| "pretraining_tp": 1, |
| "problem_type": "single_label_classification", |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": { |
| "factor": 8.0, |
| "high_freq_factor": 4.0, |
| "low_freq_factor": 1.0, |
| "original_max_position_embeddings": 8192, |
| "rope_type": "llama3" |
| }, |
| "rope_theta": 500000.0, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.44.1", |
| "use_cache": false, |
| "vocab_size": 128256 |
| } |
|
|
