| { | |
| "architectures": [ | |
| "KitGPT" | |
| ], | |
| "model_type": "kit", | |
| "vocab_size": 16000, | |
| "n_positions": 512, | |
| "n_layer": 16, | |
| "n_head": 10, | |
| "n_embd": 640, | |
| "activation": "gelu", | |
| "norm": "layernorm", | |
| "tie_word_embeddings": true, | |
| "num_parameters": 89345280, | |
| "torch_dtype": "float32" | |
| } |