Qwen3.5-Dense

Qwen3.5-9B

Qwen/Qwen3.5-9B

{
    "architectures": [
        "Qwen3_5ForConditionalGeneration"
    ],
    "image_token_id": 248056,
    "model_type": "qwen3_5",
    "text_config": {
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attn_output_gate": true,
        "dtype": "bfloat16",
        "eos_token_id": 248044,
        "full_attention_interval": 4,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "intermediate_size": 12288,
        "layer_types": [
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention"
        ],
        "linear_conv_kernel_dim": 4,
        "linear_key_head_dim": 128,
        "linear_num_key_heads": 16,
        "linear_num_value_heads": 32,
        "linear_value_head_dim": 128,
        "max_position_embeddings": 262144,
        "mlp_only_layers": [],
        "model_type": "qwen3_5_text",
        "mtp_num_hidden_layers": 1,
        "mtp_use_dedicated_embeddings": false,
        "num_attention_heads": 16,
        "num_hidden_layers": 32,
        "num_key_value_heads": 4,
        "rms_norm_eps": 1e-06,
        "use_cache": true,
        "vocab_size": 248320,
        "mamba_ssm_dtype": "float32",
        "rope_parameters": {
            "mrope_interleaved": true,
            "mrope_section": [
                11,
                11,
                10
            ],
            "rope_type": "default",
            "rope_theta": 10000000,
            "partial_rotary_factor": 0.25
        }
    },
    "tie_word_embeddings": false,
    "transformers_version": "4.57.0.dev0",
    "video_token_id": 248057,
    "vision_config": {
        "deepstack_visual_indexes": [],
        "depth": 27,
        "hidden_act": "gelu_pytorch_tanh",
        "hidden_size": 1152,
        "in_channels": 3,
        "initializer_range": 0.02,
        "intermediate_size": 4304,
        "model_type": "qwen3_5",
        "num_heads": 16,
        "num_position_embeddings": 2304,
        "out_hidden_size": 4096,
        "patch_size": 16,
        "spatial_merge_size": 2,
        "temporal_patch_size": 2
    },
    "vision_end_token_id": 248054,
    "vision_start_token_id": 248053
}

Qwen3.5-27B

Qwen/Qwen3.5-27B

{
    "architectures": [
        "Qwen3_5ForConditionalGeneration"
    ],
    "image_token_id": 248056,
    "model_type": "qwen3_5",
    "text_config": {
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attn_output_gate": true,
        "dtype": "bfloat16",
        "eos_token_id": 248044,
        "full_attention_interval": 4,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 5120,
        "initializer_range": 0.02,
        "intermediate_size": 17408,
        "layer_types": [
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention"
        ],
        "linear_conv_kernel_dim": 4,
        "linear_key_head_dim": 128,
        "linear_num_key_heads": 16,
        "linear_num_value_heads": 48,
        "linear_value_head_dim": 128,
        "max_position_embeddings": 262144,
        "mlp_only_layers": [],
        "model_type": "qwen3_5_text",
        "mtp_num_hidden_layers": 1,
        "mtp_use_dedicated_embeddings": false,
        "num_attention_heads": 24,
        "num_hidden_layers": 64,
        "num_key_value_heads": 4,
        "rms_norm_eps": 1e-06,
        "use_cache": true,
        "vocab_size": 248320,
        "mamba_ssm_dtype": "float32",
        "rope_parameters": {
            "mrope_interleaved": true,
            "mrope_section": [
                11,
                11,
                10
            ],
            "rope_type": "default",
            "rope_theta": 10000000,
            "partial_rotary_factor": 0.25
        }
    },
    "tie_word_embeddings": false,
    "transformers_version": "4.57.0.dev0",
    "video_token_id": 248057,
    "vision_config": {
        "deepstack_visual_indexes": [],
        "depth": 27,
        "hidden_act": "gelu_pytorch_tanh",
        "hidden_size": 1152,
        "in_channels": 3,
        "initializer_range": 0.02,
        "intermediate_size": 4304,
        "model_type": "qwen3_5",
        "num_heads": 16,
        "num_position_embeddings": 2304,
        "out_hidden_size": 5120,
        "patch_size": 16,
        "spatial_merge_size": 2,
        "temporal_patch_size": 2
    },
    "vision_end_token_id": 248054,
    "vision_start_token_id": 248053
}

Qwen3-Dense

Qwen3-14B

Qwen/Qwen3-14B

{
  "architectures": [
    "Qwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 5120,
  "initializer_range": 0.02,
  "intermediate_size": 17408,
  "max_position_embeddings": 40960,
  "max_window_layers": 40,
  "model_type": "qwen3",
  "num_attention_heads": 40, 
  "num_hidden_layers": 40, 
  "num_key_value_heads": 8, 
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}

Qwen3-32B

Qwen/Qwen3-32B

{
  "architectures": [
    "Qwen3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 5120, 
  "initializer_range": 0.02,
  "intermediate_size": 25600,
  "max_position_embeddings": 40960,
  "max_window_layers": 64,
  "model_type": "qwen3",
  "num_attention_heads": 64, 
  "num_hidden_layers": 64, 
  "num_key_value_heads": 8, 
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 1000000,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}

Qwen3.5-MoE

Qwen3.5-35B-A3B

Qwen/Qwen3.5-35B-A3B-Base

{
    "architectures": [
        "Qwen3_5MoeForConditionalGeneration"
    ],
    "image_token_id": 248056,
    "model_type": "qwen3_5_moe",
    "text_config": {
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attn_output_gate": true,
        "dtype": "bfloat16",
        "eos_token_id": 248044,
        "full_attention_interval": 4,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 2048,
        "initializer_range": 0.02,
        "layer_types": [
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention"
        ],
        "linear_conv_kernel_dim": 4,
        "linear_key_head_dim": 128,
        "linear_num_key_heads": 16,
        "linear_num_value_heads": 32,
        "linear_value_head_dim": 128,
        "max_position_embeddings": 262144,
        "mlp_only_layers": [],
        "model_type": "qwen3_5_moe_text",
        "moe_intermediate_size": 512,
        "mtp_num_hidden_layers": 1,
        "mtp_use_dedicated_embeddings": false,
        "num_attention_heads": 16,
        "num_experts": 256,
        "num_experts_per_tok": 8,
        "num_hidden_layers": 40,
        "num_key_value_heads": 2,
        "rms_norm_eps": 1e-06,
        "router_aux_loss_coef": 0.001,
        "shared_expert_intermediate_size": 512,
        "use_cache": true,
        "vocab_size": 248320,
        "mamba_ssm_dtype": "float32",
        "rope_parameters": {
            "mrope_interleaved": true,
            "mrope_section": [
                11,
                11,
                10
            ],
            "rope_type": "default",
            "rope_theta": 10000000,
            "partial_rotary_factor": 0.25
        }
    },
    "tie_word_embeddings": false,
    "transformers_version": "4.57.0.dev0",
    "video_token_id": 248057,
    "vision_config": {
        "deepstack_visual_indexes": [],
        "depth": 27,
        "hidden_act": "gelu_pytorch_tanh",
        "hidden_size": 1152,
        "in_channels": 3,
        "initializer_range": 0.02,
        "intermediate_size": 4304,
        "model_type": "qwen3_5_moe",
        "num_heads": 16,
        "num_position_embeddings": 2304,
        "out_hidden_size": 2048,
        "patch_size": 16,
        "spatial_merge_size": 2,
        "temporal_patch_size": 2
    },
    "vision_end_token_id": 248054,
    "vision_start_token_id": 248053
}

Qwen3.5-397B-A17B

Qwen/Qwen3.5-397B-A17B

{
    "architectures": [
        "Qwen3_5MoeForConditionalGeneration"
    ],
    "image_token_id": 248056,
    "model_type": "qwen3_5_moe",
    "text_config": {
        "attention_bias": false,
        "attention_dropout": 0.0,
        "attn_output_gate": true,
        "dtype": "bfloat16",
        "eos_token_id": 248044,
        "full_attention_interval": 4,
        "head_dim": 256,
        "hidden_act": "silu",
        "hidden_size": 4096,
        "initializer_range": 0.02,
        "layer_types": [
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention",
            "linear_attention",
            "linear_attention",
            "linear_attention",
            "full_attention"
        ],
        "linear_conv_kernel_dim": 4,
        "linear_key_head_dim": 128,
        "linear_num_key_heads": 16,
        "linear_num_value_heads": 64,
        "linear_value_head_dim": 128,
        "max_position_embeddings": 262144,
        "mlp_only_layers": [],
        "model_type": "qwen3_5_moe_text",
        "moe_intermediate_size": 1024,
        "mtp_num_hidden_layers": 1,
        "mtp_use_dedicated_embeddings": false,
        "num_attention_heads": 32,
        "num_experts": 512,
        "num_experts_per_tok": 10,
        "num_hidden_layers": 60,
        "num_key_value_heads": 2,
        "rms_norm_eps": 1e-06,
        "router_aux_loss_coef": 0.001,
        "shared_expert_intermediate_size": 1024,
        "use_cache": true,
        "vocab_size": 248320,
        "mamba_ssm_dtype": "float32",
        "rope_parameters": {
            "mrope_interleaved": true,
            "mrope_section": [
                11,
                11,
                10
            ],
            "rope_type": "default",
            "rope_theta": 10000000,
            "partial_rotary_factor": 0.25
        }
    },
    "tie_word_embeddings": false,
    "transformers_version": "4.57.0.dev0",
    "video_token_id": 248057,
    "vision_config": {
        "deepstack_visual_indexes": [],
        "depth": 27,
        "hidden_act": "gelu_pytorch_tanh",
        "hidden_size": 1152,
        "in_channels": 3,
        "initializer_range": 0.02,
        "intermediate_size": 4304,
        "model_type": "qwen3_5_moe",
        "num_heads": 16,
        "num_position_embeddings": 2304,
        "out_hidden_size": 4096,
        "patch_size": 16,
        "spatial_merge_size": 2,
        "temporal_patch_size": 2
    },
    "vision_end_token_id": 248054,
    "vision_start_token_id": 248053
}

Qwen3-MoE

Qwen3-30B-A3B-Instruct-2507

Qwen/Qwen3-30B-A3B-Instruct-2507

{
  "architectures": [
    "Qwen3MoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "decoder_sparse_step": 1,
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 2048, 
  "initializer_range": 0.02,
  "intermediate_size": 6144,
  "max_position_embeddings": 262144,
  "max_window_layers": 48,
  "mlp_only_layers": [],
  "model_type": "qwen3_moe",
  "moe_intermediate_size": 768,
  "norm_topk_prob": true,
  "num_attention_heads": 32,
  "num_experts": 128,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 48,
  "num_key_value_heads": 4,
  "output_router_logits": false,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000000,
  "router_aux_loss_coef": 0.001,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}

Qwen3-235B-A22B-Thinking-2507

Qwen/Qwen3-235B-A22B-Thinking-2507

{
  "architectures": [
    "Qwen3MoeForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "decoder_sparse_step": 1,
  "eos_token_id": 151645,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 12288,
  "max_position_embeddings": 262144,
  "max_window_layers": 94,
  "mlp_only_layers": [],
  "model_type": "qwen3_moe",
  "moe_intermediate_size": 1536,
  "norm_topk_prob": true,
  "num_attention_heads": 64,
  "num_experts": 128,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 94,
  "num_key_value_heads": 4,
  "output_router_logits": false,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 5000000,
  "router_aux_loss_coef": 0.001,
  "sliding_window": null,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}

Qwen3-Next-80B-A3B-Instruct

Qwen/Qwen3-Next-80B-A3B-Instruct

{
  "architectures": [
    "Qwen3NextForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 151643,
  "decoder_sparse_step": 1,
  "eos_token_id": 151645,
  "full_attention_interval": 4,
  "head_dim": 256,
  "hidden_act": "silu",
  "hidden_size": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 5120,
  "linear_conv_kernel_dim": 4,
  "linear_key_head_dim": 128,
  "linear_num_key_heads": 16,
  "linear_num_value_heads": 32,
  "linear_value_head_dim": 128,
  "max_position_embeddings": 262144,
  "mlp_only_layers": [],
  "model_type": "qwen3_next",
  "moe_intermediate_size": 512,
  "norm_topk_prob": true,
  "num_attention_heads": 16,
  "num_experts": 512,
  "num_experts_per_tok": 10,
  "num_hidden_layers": 48,
  "num_key_value_heads": 2,
  "output_router_logits": false,
  "partial_rotary_factor": 0.25,
  "rms_norm_eps": 1e-06,
  "rope_scaling": null,
  "rope_theta": 10000000,
  "router_aux_loss_coef": 0.001,
  "shared_expert_intermediate_size": 512,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.57.0.dev0",
  "use_cache": true,
  "use_sliding_window": false,
  "vocab_size": 151936
}

DeepSeek 系列

DeepSeek-V3.2

deepseek-ai/DeepSeek-V3.2

{
  "architectures": [
    "DeepseekV32ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "eos_token_id": 1,
  "ep_size": 1,
  "first_k_dense_replace": 3,
  "hidden_act": "silu",
  "hidden_size": 7168,
  "index_head_dim": 128,
  "index_n_heads": 64,
  "index_topk": 2048,
  "initializer_range": 0.02,
  "intermediate_size": 18432,
  "kv_lora_rank": 512,
  "max_position_embeddings": 163840,
  "model_type": "deepseek_v32",
  "moe_intermediate_size": 2048,
  "moe_layer_freq": 1,
  "n_group": 8,
  "n_routed_experts": 256,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "num_attention_heads": 128,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 61,
  "num_key_value_heads": 128,
  "num_nextn_predict_layers": 1,
  "q_lora_rank": 1536,
  "qk_nope_head_dim": 128,
  "qk_rope_head_dim": 64,
  "quantization_config": {
    "activation_scheme": "dynamic",
    "fmt": "e4m3",
    "quant_method": "fp8",
    "scale_fmt": "ue8m0",
    "weight_block_size": [
      128,
      128
    ]
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "beta_fast": 32,
    "beta_slow": 1,
    "factor": 40,
    "mscale": 1.0,
    "mscale_all_dim": 1.0,
    "original_max_position_embeddings": 4096,
    "type": "yarn"
  },
  "rope_theta": 10000,
  "routed_scaling_factor": 2.5,
  "scoring_func": "sigmoid",
  "tie_word_embeddings": false,
  "topk_group": 4,
  "topk_method": "noaux_tc",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.44.2",
  "use_cache": true,
  "v_head_dim": 128,
  "vocab_size": 129280
}

DeepSeek-R1

deepseek-ai/DeepSeek-R1

{
  "architectures": [
    "DeepseekV3ForCausalLM"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_deepseek.DeepseekV3Config",
    "AutoModel": "modeling_deepseek.DeepseekV3Model",
    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
  },
  "bos_token_id": 0,
  "eos_token_id": 1,
  "ep_size": 1,
  "first_k_dense_replace": 3,
  "hidden_act": "silu",
  "hidden_size": 7168,
  "initializer_range": 0.02,
  "intermediate_size": 18432,
  "kv_lora_rank": 512,
  "max_position_embeddings": 163840,
  "model_type": "deepseek_v3",
  "moe_intermediate_size": 2048,
  "moe_layer_freq": 1,
  "n_group": 8,
  "n_routed_experts": 256,
  "n_shared_experts": 1,
  "norm_topk_prob": true,
  "num_attention_heads": 128,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 61,
  "num_key_value_heads": 128,
  "num_nextn_predict_layers": 1,
  "q_lora_rank": 1536,
  "qk_nope_head_dim": 128,
  "qk_rope_head_dim": 64,
  "quantization_config": {
    "activation_scheme": "dynamic",
    "fmt": "e4m3",
    "quant_method": "fp8",
    "weight_block_size": [
      128,
      128
    ]
  },
  "rms_norm_eps": 1e-06,
  "rope_scaling": {
    "beta_fast": 32,
    "beta_slow": 1,
    "factor": 40,
    "mscale": 1.0,
    "mscale_all_dim": 1.0,
    "original_max_position_embeddings": 4096,
    "type": "yarn"
  },
  "rope_theta": 10000,
  "routed_scaling_factor": 2.5,
  "scoring_func": "sigmoid",
  "tie_word_embeddings": false,
  "topk_group": 4,
  "topk_method": "noaux_tc",
  "torch_dtype": "bfloat16",
  "transformers_version": "4.46.3",
  "use_cache": true,
  "v_head_dim": 128,
  "vocab_size": 129280
}

gpt-oss 系列

gpt-oss-120b

openai/gpt-oss-120b

{
  "architectures": [
    "GptOssForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "eos_token_id": 200002,
  "experts_per_token": 4,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2880,
  "initial_context_length": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 2880,
  "layer_types": [
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "model_type": "gpt_oss",
  "num_attention_heads": 64,
  "num_experts_per_tok": 4,
  "num_hidden_layers": 36,
  "num_key_value_heads": 8,
  "num_local_experts": 128,
  "output_router_logits": false,
  "pad_token_id": 199999,
  "quantization_config": {
    "modules_to_not_convert": [
      "model.layers.*.self_attn",
      "model.layers.*.mlp.router",
      "model.embed_tokens",
      "lm_head"
    ],
    "quant_method": "mxfp4"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 32.0,
    "original_max_position_embeddings": 4096,
    "rope_type": "yarn",
    "truncate": false
  },
  "rope_theta": 150000,
  "router_aux_loss_coef": 0.9,
  "sliding_window": 128,
  "swiglu_limit": 7.0,
  "tie_word_embeddings": false,
  "transformers_version": "4.55.0.dev0",
  "use_cache": true,
  "vocab_size": 201088
}

gpt-oss-20b

openai/gpt-oss-20b

{
  "architectures": [
    "GptOssForCausalLM"
  ],
  "attention_bias": true,
  "attention_dropout": 0.0,
  "eos_token_id": 200002,
  "experts_per_token": 4,
  "head_dim": 64,
  "hidden_act": "silu",
  "hidden_size": 2880,
  "initial_context_length": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 2880,
  "layer_types": [
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention",
    "sliding_attention",
    "full_attention"
  ],
  "max_position_embeddings": 131072,
  "model_type": "gpt_oss",
  "num_attention_heads": 64,
  "num_experts_per_tok": 4,
  "num_hidden_layers": 24,
  "num_key_value_heads": 8,
  "num_local_experts": 32,
  "output_router_logits": false,
  "pad_token_id": 199999,
  "quantization_config": {
    "modules_to_not_convert": [
      "model.layers.*.self_attn",
      "model.layers.*.mlp.router",
      "model.embed_tokens",
      "lm_head"
    ],
    "quant_method": "mxfp4"
  },
  "rms_norm_eps": 1e-05,
  "rope_scaling": {
    "beta_fast": 32.0,
    "beta_slow": 1.0,
    "factor": 32.0,
    "original_max_position_embeddings": 4096,
    "rope_type": "yarn",
    "truncate": false
  },
  "rope_theta": 150000,
  "router_aux_loss_coef": 0.9,
  "sliding_window": 128,
  "swiglu_limit": 7.0,
  "tie_word_embeddings": false,
  "transformers_version": "4.55.0.dev0",
  "use_cache": true,
  "vocab_size": 201088
}