{ "_name_or_path": "ridger/hgrn_bit_3B_100B_realbit", "architectures": [ "HGRNBitForCausalLM" ], "attn_mode": "fused_recurrent", "bos_token_id": 1, "conv_size": 4, "eos_token_id": 2, "expand_ratio": 1, "fuse_cross_entropy": true, "hidden_act": "swish", "hidden_ratio": 4, "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": null, "max_position_embeddings": 2048, "model_type": "hgrn_bit", "num_heads": 1, "num_hidden_layers": 32, "rms_norm_eps": 1e-06, "share_conv_kernel": true, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.40.2", "use_cache": true, "use_lower_bound": true, "use_short_conv": false, "vocab_size": 32000 }