CoolFace
Modelpublic

COURSEMO/coursemo_model_final

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
0likes35downloads
config.json210 linesDownload Raw Back to root
1{2    "architectures": [3        "Qwen2_5_VLForConditionalGeneration"4    ],5    "attention_dropout": 0.0,6    "eos_token_id": 151645,7    "hidden_act": "silu",8    "hidden_size": 8192,9    "image_token_id": 151655,10    "initializer_range": 0.02,11    "intermediate_size": 29568,12    "max_position_embeddings": 128000,13    "max_window_layers": 80,14    "model_type": "qwen2_5_vl",15    "num_attention_heads": 64,16    "num_hidden_layers": 80,17    "num_key_value_heads": 8,18    "pad_token_id": 151654,19    "rms_norm_eps": 1e-06,20    "rope_scaling": {21        "mrope_section": [22            16,23            24,24            2425        ],26        "rope_type": "default",27        "type": "default"28    },29    "rope_theta": 1000000.0,30    "sliding_window": 32768,31    "text_config": {32        "architectures": [33            "Qwen2_5_VLForConditionalGeneration"34        ],35        "attention_dropout": 0.0,36        "eos_token_id": 151645,37        "hidden_act": "silu",38        "hidden_size": 8192,39        "image_token_id": null,40        "initializer_range": 0.02,41        "intermediate_size": 29568,42        "layer_types": [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            "full_attention",57            "full_attention",58            "full_attention",59            "full_attention",60            "full_attention",61            "full_attention",62            "full_attention",63            "full_attention",64            "full_attention",65            "full_attention",66            "full_attention",67            "full_attention",68            "full_attention",69            "full_attention",70            "full_attention",71            "full_attention",72            "full_attention",73            "full_attention",74            "full_attention",75            "full_attention",76            "full_attention",77            "full_attention",78            "full_attention",79            "full_attention",80            "full_attention",81            "full_attention",82            "full_attention",83            "full_attention",84            "full_attention",85            "full_attention",86            "full_attention",87            "full_attention",88            "full_attention",89            "full_attention",90            "full_attention",91            "full_attention",92            "full_attention",93            "full_attention",94            "full_attention",95            "full_attention",96            "full_attention",97            "full_attention",98            "full_attention",99            "full_attention",100            "full_attention",101            "full_attention",102            "full_attention",103            "full_attention",104            "full_attention",105            "full_attention",106            "full_attention",107            "full_attention",108            "full_attention",109            "full_attention",110            "full_attention",111            "full_attention",112            "full_attention",113            "full_attention",114            "full_attention",115            "full_attention",116            "full_attention",117            "full_attention",118            "full_attention",119            "full_attention",120            "full_attention",121            "full_attention",122            "full_attention"123        ],124        "max_position_embeddings": 128000,125        "max_window_layers": 80,126        "model_type": "qwen2_5_vl_text",127        "num_attention_heads": 64,128        "num_hidden_layers": 80,129        "num_key_value_heads": 8,130        "pad_token_id": 151654,131        "quantization_config": {132            "_load_in_4bit": true,133            "_load_in_8bit": false,134            "bnb_4bit_compute_dtype": "bfloat16",135            "bnb_4bit_quant_storage": "uint8",136            "bnb_4bit_quant_type": "nf4",137            "bnb_4bit_use_double_quant": true,138            "llm_int8_enable_fp32_cpu_offload": false,139            "llm_int8_has_fp16_weight": false,140            "llm_int8_skip_modules": [141                "lm_head",142                "multi_modal_projector",143                "merger",144                "modality_projection"145            ],146            "llm_int8_threshold": 6.0,147            "load_in_4bit": true,148            "load_in_8bit": false,149            "quant_method": "bitsandbytes"150        },151        "rms_norm_eps": 1e-06,152        "rope_scaling": {153            "mrope_section": [154                16,155                24,156                24157            ],158            "rope_type": "default",159            "type": "default"160        },161        "rope_theta": 1000000.0,162        "sliding_window": null,163        "torch_dtype": "bfloat16",164        "unsloth_fixed": true,165        "use_cache": true,166        "use_sliding_window": false,167        "video_token_id": null,168        "vision_end_token_id": 151653,169        "vision_start_token_id": 151652,170        "vision_token_id": 151654,171        "vocab_size": 152064172    },173    "tie_word_embeddings": false,174    "torch_dtype": "bfloat16",175    "transformers_version": "4.53.3",176    "unsloth_fixed": true,177    "unsloth_version": "2025.7.7",178    "use_cache": true,179    "use_sliding_window": false,180    "video_token_id": 151656,181    "vision_config": {182        "depth": 32,183        "fullatt_block_indexes": [184            7,185            15,186            23,187            31188        ],189        "hidden_act": "silu",190        "hidden_size": 1280,191        "in_channels": 3,192        "in_chans": 3,193        "initializer_range": 0.02,194        "intermediate_size": 3456,195        "model_type": "qwen2_5_vl",196        "num_heads": 16,197        "out_hidden_size": 8192,198        "patch_size": 14,199        "spatial_merge_size": 2,200        "spatial_patch_size": 14,201        "temporal_patch_size": 2,202        "tokens_per_second": 2,203        "torch_dtype": "bfloat16",204        "window_size": 112205    },206    "vision_end_token_id": 151653,207    "vision_start_token_id": 151652,208    "vision_token_id": 151654,209    "vocab_size": 152064210}