CoolFace
Modelpublic

tencent/Sequential-Hidden-Decoding-8B-n8-Instruct

sourceHugging Faceotherupdated 6mo agoView on Hugging Face
8likes188downloads
config.json75 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen3ScaleSeqForCausalLM"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "auto_map": {8    "AutoConfig": "configuration_qwen3_scale_seq.Qwen3ScaleSeqConfig",9    "AutoModel": "modeling_qwen3_scale_seq.Qwen3ScaleSeqModel",10    "AutoModelForCausalLM": "modeling_qwen3_scale_seq.Qwen3ScaleSeqForCausalLM"11  },12  "dtype": "bfloat16",13  "eos_token_id": 151643,14  "head_dim": 128,15  "hidden_act": "silu",16  "hidden_size": 4096,17  "initializer_range": 0.02,18  "intermediate_size": 12288,19  "layer_types": [20    "full_attention",21    "full_attention",22    "full_attention",23    "full_attention",24    "full_attention",25    "full_attention",26    "full_attention",27    "full_attention",28    "full_attention",29    "full_attention",30    "full_attention",31    "full_attention",32    "full_attention",33    "full_attention",34    "full_attention",35    "full_attention",36    "full_attention",37    "full_attention",38    "full_attention",39    "full_attention",40    "full_attention",41    "full_attention",42    "full_attention",43    "full_attention",44    "full_attention",45    "full_attention",46    "full_attention",47    "full_attention",48    "full_attention",49    "full_attention",50    "full_attention",51    "full_attention",52    "full_attention",53    "full_attention",54    "full_attention",55    "full_attention"56  ],57  "max_position_embeddings": 131072,58  "max_window_layers": 28,59  "model_type": "qwen3_scale_seq",60  "num_attention_heads": 32,61  "num_hidden_layers": 36,62  "num_key_value_heads": 8,63  "pad_token_id": 151643,64  "rms_norm_eps": 1e-06,65  "rope_scaling": null,66  "rope_theta": 1000000.0,67  "scale_seq_times": 7,68  "sliding_window": null,69  "tie_word_embeddings": false,70  "torch_dtype": "bfloat16",71  "transformers_version": "4.57.1",72  "use_cache": true,73  "use_sliding_window": false,74  "vocab_size": 15193675}