| { | |
| "_name_or_path": "/root/pretraining/local-models/training/2024-03-12_22-15-53", | |
| "alibi": true, | |
| "apply_residual_connection_post_layernorm": false, | |
| "architectures": [ | |
| "FalconForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_falcon.FalconConfig", | |
| "AutoModel": "modeling_falcon.FalconModel", | |
| "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM", | |
| "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering", | |
| "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification", | |
| "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification" | |
| }, | |
| "bias": true, | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_position_embeddings": 2048, | |
| "model_type": "falcon", | |
| "multi_query": false, | |
| "new_decoder_architecture": false, | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 24, | |
| "num_kv_heads": 32, | |
| "parallel_attn": false, | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.38.0", | |
| "use_cache": true, | |
| "vocab_size": 50304 | |
| } | |