| { | |
| "architectures": ["BitNetForCausalLM"], | |
| "model_type": "bitnet", | |
| "vocab_size": 32000, | |
| "hidden_size": 768, | |
| "num_hidden_layers": 12, | |
| "num_attention_heads": 12, | |
| "intermediate_size": 3072, | |
| "hidden_act": "gelu", | |
| "max_position_embeddings": 512, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-12, | |
| "dropout": 0.1, | |
| "pad_token_id": 0, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "torch_dtype": "float32" | |
| } |