explosion-testing/refined-web-model-test
03k
1{2 "_name_or_path": "tiiuae/falcon-7b",3 "alibi": false,4 "apply_residual_connection_post_layernorm": false,5 "architectures": [6 "RWForCausalLM"7 ],8 "attention_dropout": 0.0,9 "auto_map": {10 "AutoConfig": "configuration_RW.RWConfig",11 "AutoModel": "modelling_RW.RWModel",12 "AutoModelForCausalLM": "modelling_RW.RWForCausalLM",13 "AutoModelForQuestionAnswering": "modelling_RW.RWForQuestionAnswering",14 "AutoModelForSequenceClassification": "modelling_RW.RWForSequenceClassification",15 "AutoModelForTokenClassification": "modelling_RW.RWForTokenClassification"16 },17 "bias": false,18 "bos_token_id": 11,19 "eos_token_id": 11,20 "hidden_dropout": 0.0,21 "hidden_size": 32,22 "initializer_range": 0.02,23 "layer_norm_epsilon": 1e-05,24 "model_type": "RefinedWebModel",25 "multi_query": true,26 "n_head": 4,27 "n_layer": 5,28 "parallel_attn": true,29 "torch_dtype": "float32",30 "transformers_version": "4.28.1",31 "type_vocab_size": 16,32 "use_cache": true,33 "vocab_size": 102434}35 