{ "architectures": [ "GlmForCausalLM" ], "auto_map": { "AutoConfig": "configuration_glm.GlmConfig", "AutoModel": "modeling_glm.GlmModel", "AutoModelForCausalLM": "modeling_glm.GlmForCausalLM", "AutoModelForSequenceClassification": "modeling_glm.GlmForSequenceClassification" }, "attention_bias": false, "attention_dropout": 0.0, "boi_token_id": 59256, "eoi_token_id": 59257, "eos_token_id": [ 59246, 59253, 59255 ], "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 6144, "max_position_embeddings": 4096, "model_type": "glm", "num_attention_heads": 16, "num_hidden_layers": 28, "num_key_value_heads": 4, "pad_token_id": 59246, "partial_rotary_factor": 1.0, "rms_norm_eps": 1e-05, "rope_theta": 10000.0, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.47.0.dev0", "use_cache": true, "vision_config": { "hidden_size": 1152, "image_size": 672, "intermediate_size": 4304, "model_type": "siglip_vision_model", "num_attention_heads": 16, "num_hidden_layers": 27, "patch_size": 14, "torch_dtype": "bfloat16" }, "vocab_size": 59264 }