| { | |
| "architectures": [ | |
| "Glm4vForConditionalGeneration" | |
| ], | |
| "model_type": "glm4v", | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "pad_token_id": 151329, | |
| "eos_token_id": [ | |
| 151329, | |
| 151336, | |
| 151338, | |
| 151348 | |
| ], | |
| "image_start_token_id": 151339, | |
| "image_end_token_id": 151340, | |
| "video_start_token_id": 151341, | |
| "video_end_token_id": 151342, | |
| "image_token_id": 151343, | |
| "video_token_id": 151344, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13696, | |
| "max_position_embeddings": 65536, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.53.0dev", | |
| "use_cache": true, | |
| "vocab_size": 151552, | |
| "partial_rotary_factor": 0.5, | |
| "vision_config": { | |
| "hidden_size": 1536, | |
| "depth": 24, | |
| "num_heads": 12, | |
| "attention_bias": false, | |
| "intermediate_size": 13696, | |
| "hidden_act": "silu", | |
| "hidden_dropout_prob": 0.0, | |
| "initializer_range": 0.02, | |
| "image_size": 336, | |
| "patch_size": 14, | |
| "out_hidden_size": 4096, | |
| "rms_norm_eps": 1e-05, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "rope_scaling": { | |
| "type": "default", | |
| "mrope_section": [ | |
| 8, | |
| 12, | |
| 12 | |
| ] | |
| } | |
| } |