clibrain/lince-zero
4850
1{2 "alibi": false,3 "apply_residual_connection_post_layernorm": false,4 "architectures": [5 "FalconForCausalLM"6 ],7 "attention_dropout": 0.0,8 "auto_map": {9 "AutoConfig": "configuration_falcon.FalconConfig",10 "AutoModel": "modeling_falcon.FalconModel",11 "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",12 "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification",13 "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",14 "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM"15 },16 "bias": false,17 "bos_token_id": 11,18 "eos_token_id": 11,19 "hidden_dropout": 0.0,20 "hidden_size": 4544,21 "initializer_range": 0.02,22 "layer_norm_epsilon": 1e-05,23 "model_type": "falcon",24 "multi_query": true,25 "new_decoder_architecture": false,26 "num_attention_heads": 71,27 "num_hidden_layers": 32,28 "parallel_attn": true,29 "torch_dtype": "bfloat16",30 "transformers_version": "4.27.4",31 "use_cache": true,32 "vocab_size": 6502433}