| { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "hidden_act": "silu", | |
| "hidden_size": 1536, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8960, | |
| "max_position_embeddings": 4096, | |
| "max_window_layers": 21, | |
| "model_type": "llama", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 2, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 10000.0, | |
| "rope_scaling": null, | |
| "sliding_window": 4096, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.37.0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } |