| { | |
| "_name_or_path": "output/pretrain_model_hf", | |
| "architectures": [ | |
| "Transformer" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "config.ModelConfig", | |
| "AutoModelForCausalLM": "model.Transformer" | |
| }, | |
| "dim": 512, | |
| "dropout": 0.0, | |
| "flash_attn": true, | |
| "hidden_dim": null, | |
| "max_seq_len": 512, | |
| "model_type": "IntelliKernel", | |
| "multiple_of": 64, | |
| "n_heads": 16, | |
| "n_kv_heads": 8, | |
| "n_layers": 8, | |
| "norm_eps": 1e-05, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.46.0", | |
| "vocab_size": 6400 | |
| } | |