CoolFace
Modelpublic

TeleAI-AI-Flow/AI-FLow-OpticsReview-9B

sourceHugging Facecc-by-nc-4.0updated 2d agoView on Hugging Face
0likes17downloads
config.json113 linesDownload Raw Back to root
1{2  "architectures": [3    "Qwen3_5ForConditionalGeneration"4  ],5  "bos_token_id": null,6  "dtype": "bfloat16",7  "eos_token_id": 248046,8  "image_token_id": 248056,9  "model_type": "qwen3_5",10  "pad_token_id": 248044,11  "text_config": {12    "attention_bias": false,13    "attention_dropout": 0.0,14    "attn_output_gate": true,15    "bos_token_id": null,16    "dtype": "bfloat16",17    "eos_token_id": 248044,18    "full_attention_interval": 4,19    "head_dim": 256,20    "hidden_act": "silu",21    "hidden_size": 4096,22    "initializer_range": 0.02,23    "intermediate_size": 12288,24    "layer_types": [25      "linear_attention",26      "linear_attention",27      "linear_attention",28      "full_attention",29      "linear_attention",30      "linear_attention",31      "linear_attention",32      "full_attention",33      "linear_attention",34      "linear_attention",35      "linear_attention",36      "full_attention",37      "linear_attention",38      "linear_attention",39      "linear_attention",40      "full_attention",41      "linear_attention",42      "linear_attention",43      "linear_attention",44      "full_attention",45      "linear_attention",46      "linear_attention",47      "linear_attention",48      "full_attention",49      "linear_attention",50      "linear_attention",51      "linear_attention",52      "full_attention",53      "linear_attention",54      "linear_attention",55      "linear_attention",56      "full_attention"57    ],58    "linear_conv_kernel_dim": 4,59    "linear_key_head_dim": 128,60    "linear_num_key_heads": 16,61    "linear_num_value_heads": 32,62    "linear_value_head_dim": 128,63    "mamba_ssm_dtype": "float32",64    "max_position_embeddings": 262144,65    "mlp_only_layers": [],66    "model_type": "qwen3_5_text",67    "mtp_num_hidden_layers": 0,68    "mtp_use_dedicated_embeddings": false,69    "num_attention_heads": 16,70    "num_hidden_layers": 32,71    "num_key_value_heads": 4,72    "pad_token_id": null,73    "partial_rotary_factor": 0.25,74    "rms_norm_eps": 1e-06,75    "rope_parameters": {76      "mrope_interleaved": true,77      "mrope_section": [78        11,79        11,80        1081      ],82      "partial_rotary_factor": 0.25,83      "rope_theta": 10000000,84      "rope_type": "default"85    },86    "tie_word_embeddings": false,87    "use_cache": true,88    "vocab_size": 24832089  },90  "tie_word_embeddings": false,91  "transformers_version": "5.12.1",92  "video_token_id": 248057,93  "vision_config": {94    "deepstack_visual_indexes": [],95    "depth": 27,96    "dtype": "bfloat16",97    "hidden_act": "gelu_pytorch_tanh",98    "hidden_size": 1152,99    "in_channels": 3,100    "initializer_range": 0.02,101    "intermediate_size": 4304,102    "model_type": "qwen3_5_vision",103    "num_heads": 16,104    "num_position_embeddings": 2304,105    "out_hidden_size": 4096,106    "patch_size": 16,107    "spatial_merge_size": 2,108    "temporal_patch_size": 2109  },110  "vision_end_token_id": 248054,111  "vision_start_token_id": 248053112}113