{ "alibi": true, "apply_residual_connection_post_layernorm": false, "architectures": [ "FalconForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_RW.RWConfig", "AutoModel": "modeling_RW.RWModel", "AutoModelForSequenceClassification": "modeling_RW.RWForSequenceClassification", "AutoModelForTokenClassification": "modeling_RW.RWForTokenClassification", "AutoModelForQuestionAnswering": "modeling_RW.RWForQuestionAnswering", "AutoModelForCausalLM": "modeling_RW.RWForCausalLM" }, "bias": true, "bos_token_id": 1, "eos_token_id": 2, "hidden_dropout": 0.0, "hidden_size": 2048, "initializer_range": 0.02, "layer_norm_epsilon": 1e-05, "model_type": "falcon", "multi_query": false, "new_decoder_architecture": false, "num_attention_heads": 32, "num_hidden_layers": 24, "parallel_attn": false, "torch_dtype": "bfloat16", "transformers_version": "4.27.4", "use_cache": true, "vocab_size": 50304 }