| { | |
| "_name_or_path": "/workspace/pretraining/local-models/training/2023-12-31_21-30-05", | |
| "alibi": false, | |
| "architectures": [ | |
| "FalconForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bias": false, | |
| "bos_token_id": 11, | |
| "eos_token_id": 11, | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_position_embeddings": 1024, | |
| "model_type": "falcon", | |
| "multi_query": true, | |
| "new_decoder_architecture": false, | |
| "num_attention_heads": 64, | |
| "num_hidden_layers": 4, | |
| "num_kv_heads": 64, | |
| "parallel_attn": true, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.34.1", | |
| "use_cache": true, | |
| "vocab_size": 65024 | |
| } | |