| { | |
| "architectures": [ | |
| "GlmForCausalLM" | |
| ], | |
| "partial_rotary_factor": 1.0, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "eos_token_id": [ | |
| 59246, | |
| 59253, | |
| 59255 | |
| ], | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 3072, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 8192, | |
| "model_type": "glm", | |
| "num_attention_heads": 24, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 6, | |
| "pad_token_id": 59246, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.47.0.dev0", | |
| "use_cache": true, | |
| "vocab_size": 59264 | |
| } | |