{ "architectures": [ "HGRN2ForCausalLM" ], "attn_mode": "chunk", "bos_token_id": 1, "conv_size": 4, "elementwise_affine": true, "eos_token_id": 2, "expand_ratio": 128, "fuse_cross_entropy": true, "hidden_act": "swish", "hidden_ratio": 4, "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": null, "max_position_embeddings": 2048, "model_type": "hgrn2", "norm_eps": 1e-06, "num_heads": null, "num_hidden_layers": 26, "tie_word_embeddings": false, "torch_dtype": "float32", "transformers_version": "4.44.1", "use_cache": true, "use_lower_bound": true, "use_short_conv": false, "vocab_size": 32000, "auto_map": { "AutoConfig": "configuration_hgrn2.HGRN2Config", "AutoModelForCausalLM": "modeling_hgrn2.HGRN2ForCausalLM", "AutoModel": "modeling_hgrn2.HGRN2Model", "AutoModelForSequenceClassification": "modeling_hgrn2.HGRN2ForSequenceClassification" } }