| { | |
| "_name_or_path": "/bscdata/models/falcon_7b_balanced_tokenizer_fp16/", | |
| "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": 50256, | |
| "eos_token_id": 50256, | |
| "hidden_dropout": 0.0, | |
| "hidden_size": 4544, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "falcon", | |
| "multi_query": true, | |
| "n_head": 71, | |
| "n_layer": 32, | |
| "pad_token_id": 50256, | |
| "parallel_attn": true, | |
| "torch_dtype": "float16", | |
| "transformers_version": "4.30.2", | |
| "use_cache": true, | |
| "max_position_embeddings": 2048, | |
| "vocab_size": 50257 | |
| } | |