CoolFace
Modelpublic

infly/Infinity-Parser2-Pro

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
95likes29kdownloads
config.json128 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen3_5MoeForConditionalGeneration"4  ],5  "bos_token_id": null,6  "dtype": "bfloat16",7  "eos_token_id": 248046,8  "hidden_size": 2048,9  "image_token_id": 248056,10  "model_type": "qwen3_5_moe",11  "pad_token_id": 248044,12  "rope_theta": 10000000,13  "text_config": {14    "attention_bias": false,15    "attention_dropout": 0.0,16    "attn_output_gate": true,17    "bos_token_id": null,18    "dtype": "bfloat16",19    "eos_token_id": 248044,20    "full_attention_interval": 4,21    "head_dim": 256,22    "hidden_act": "silu",23    "hidden_size": 2048,24    "initializer_range": 0.02,25    "layer_types": [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      "linear_attention",51      "linear_attention",52      "linear_attention",53      "full_attention",54      "linear_attention",55      "linear_attention",56      "linear_attention",57      "full_attention",58      "linear_attention",59      "linear_attention",60      "linear_attention",61      "full_attention",62      "linear_attention",63      "linear_attention",64      "linear_attention",65      "full_attention"66    ],67    "linear_conv_kernel_dim": 4,68    "linear_key_head_dim": 128,69    "linear_num_key_heads": 16,70    "linear_num_value_heads": 32,71    "linear_value_head_dim": 128,72    "mamba_ssm_dtype": "float32",73    "max_position_embeddings": 262144,74    "mlp_only_layers": [],75    "model_type": "qwen3_5_moe_text",76    "moe_intermediate_size": 512,77    "mtp_num_hidden_layers": 1,78    "mtp_use_dedicated_embeddings": false,79    "num_attention_heads": 16,80    "num_experts": 256,81    "num_experts_per_tok": 8,82    "num_hidden_layers": 40,83    "num_key_value_heads": 2,84    "output_router_logits": false,85    "pad_token_id": null,86    "partial_rotary_factor": 0.25,87    "rms_norm_eps": 1e-06,88    "rope_parameters": {89      "mrope_interleaved": true,90      "mrope_section": [91        11,92        11,93        1094      ],95      "partial_rotary_factor": 0.25,96      "rope_theta": 10000000,97      "rope_type": "default"98    },99    "router_aux_loss_coef": 0.001,100    "shared_expert_intermediate_size": 512,101    "tie_word_embeddings": false,102    "use_cache": true,103    "vocab_size": 248320104  },105  "tie_word_embeddings": false,106  "transformers_version": "5.3.0",107  "video_token_id": 248057,108  "vision_config": {109    "deepstack_visual_indexes": [],110    "depth": 27,111    "dtype": "bfloat16",112    "hidden_act": "gelu_pytorch_tanh",113    "hidden_size": 1152,114    "in_channels": 3,115    "initializer_range": 0.02,116    "intermediate_size": 4304,117    "model_type": "qwen3_5_moe",118    "num_heads": 16,119    "num_position_embeddings": 2304,120    "out_hidden_size": 2048,121    "patch_size": 16,122    "spatial_merge_size": 2,123    "temporal_patch_size": 2124  },125  "vision_end_token_id": 248054,126  "vision_start_token_id": 248053127}128