jploski's picture
End of training
4443248
{
"_name_or_path": "./falcon-mini-shakespeare",
"alibi": false,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"RWForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_RW.RWConfig",
"AutoModel": "modelling_RW.RWModel",
"AutoModelForCausalLM": "modelling_RW.RWForCausalLM",
"AutoModelForQuestionAnswering": "modelling_RW.RWForQuestionAnswering",
"AutoModelForSequenceClassification": "modelling_RW.RWForSequenceClassification",
"AutoModelForTokenClassification": "modelling_RW.RWForTokenClassification"
},
"bias": false,
"bos_token_id": 11,
"eos_token_id": 11,
"hidden_dropout": 0.0,
"hidden_size": 128,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "RefinedWebModel",
"multi_query": true,
"n_head": 4,
"n_layer": 8,
"parallel_attn": true,
"torch_dtype": "float32",
"transformers_version": "4.28.0",
"use_cache": true,
"vocab_size": 65024
}