| { | |
| "alibi": false, | |
| "apply_residual_connection_post_layernorm": false, | |
| "architectures": [ | |
| "FalconForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_falcon.FalconConfig", | |
| "AutoModel": "modeling_falcon.FalconModel", | |
| "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification", | |
| "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification", | |
| "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering", | |
| "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM" | |
| }, | |
| "bias": false, | |
| "bos_token_id": 11, | |
| "eos_token_id": 11, | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 4544, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "falcon", | |
| "multi_query": true, | |
| "new_decoder_architecture": false, | |
| "num_attention_heads": 71, | |
| "num_hidden_layers": 32, | |
| "parallel_attn": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.27.4", | |
| "use_cache": true, | |
| "vocab_size": 65024, | |
| "finetuning_task": "text-generation", | |
| "learning_rate": 2e-4 | |
| } |