RecursiveMAS/Sequential-Scaled-Solver-Qwen3.5-4B
0138
1{2 "architectures": [3 "Qwen3_5ForCausalLM"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "attn_output_gate": true,8 "bos_token_id": null,9 "dtype": "bfloat16",10 "eos_token_id": 248044,11 "full_attention_interval": 4,12 "head_dim": 256,13 "hidden_act": "silu",14 "hidden_size": 2560,15 "initializer_range": 0.02,16 "intermediate_size": 9216,17 "layer_types": [18 "linear_attention",19 "linear_attention",20 "linear_attention",21 "full_attention",22 "linear_attention",23 "linear_attention",24 "linear_attention",25 "full_attention",26 "linear_attention",27 "linear_attention",28 "linear_attention",29 "full_attention",30 "linear_attention",31 "linear_attention",32 "linear_attention",33 "full_attention",34 "linear_attention",35 "linear_attention",36 "linear_attention",37 "full_attention",38 "linear_attention",39 "linear_attention",40 "linear_attention",41 "full_attention",42 "linear_attention",43 "linear_attention",44 "linear_attention",45 "full_attention",46 "linear_attention",47 "linear_attention",48 "linear_attention",49 "full_attention"50 ],51 "linear_conv_kernel_dim": 4,52 "linear_key_head_dim": 128,53 "linear_num_key_heads": 16,54 "linear_num_value_heads": 32,55 "linear_value_head_dim": 128,56 "mamba_ssm_dtype": "float32",57 "max_position_embeddings": 262144,58 "mlp_only_layers": [],59 "model_type": "qwen3_5_text",60 "mtp_num_hidden_layers": 1,61 "mtp_use_dedicated_embeddings": false,62 "num_attention_heads": 16,63 "num_hidden_layers": 32,64 "num_key_value_heads": 4,65 "pad_token_id": null,66 "partial_rotary_factor": 0.25,67 "rms_norm_eps": 1e-06,68 "rope_parameters": {69 "mrope_interleaved": true,70 "mrope_section": [71 11,72 11,73 1074 ],75 "partial_rotary_factor": 0.25,76 "rope_theta": 10000000,77 "rope_type": "default"78 },79 "tie_word_embeddings": true,80 "transformers_version": "5.3.0",81 "use_cache": true,82 "vocab_size": 24832083}84 