{ "architectures": [ "NeoLMForCausalLM" ], "auto_map": { "AutoConfig": "configuration_neolm.NeoLMConfig", "AutoModelForCausalLM": "modeling_neolm.NeoLMForCausalLM", "AutoModelForSequenceClassification": "modeling_neolm.NeoLMForSequenceClassification" }, "bos_token_id": null, "dropout": 0.1, "dtype": "bfloat16", "eos_token_id": 0, "hidden_size": 512, "intermediate_size": 1536, "max_position_embeddings": 1024, "mlp_multiple_of": 256, "model_type": "neolm", "num_attention_heads": 8, "num_hidden_layers": 12, "num_key_value_heads": 2, "pad_token_id": 1, "qk_norm": true, "rms_norm_eps": 1e-06, "rope_base": 10000, "scale_residual_init": true, "tie_word_embeddings": true, "transformers_version": "5.14.1", "use_cache": true, "vocab_size": 49152 }