{ "_name_or_path": "SPM-50M-Alpha", "architectures": [ "LlamaForCausalLM" ], "model_type": "llama", "bos_token_id": 2, "eos_token_id": 3, "pad_token_id": 0, "hidden_size": 512, "intermediate_size": 1536, "num_hidden_layers": 12, "num_attention_heads": 8, "num_key_value_heads": 4, "max_position_embeddings": 2048, "vocab_size": 32000, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "hidden_act": "silu", "attention_bias": false, "attention_dropout": 0.0, "initializer_range": 0.02, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.40.0", "spm_version": "0.1.0" }