venus-x1 / config.json
shithumb's picture
Upload 5 files
c1106d7 verified
{
"alibi": true,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"VenusForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_venus.VenusConfig",
"AutoModel": "modeling_venus.VenusModel",
"AutoModelForSequenceClassification": "modeling_venus.VenusForSequenceClassification",
"AutoModelForTokenClassification": "modeling_venus.VenusForTokenClassification",
"AutoModelForQuestionAnswering": "modeling_venus.VenusForQuestionAnswering",
"AutoModelForCausalLM": "modeling_venus.VenusForCausalLM"
},
"bias": true,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_dropout": 0.0,
"hidden_size": 2048,
"initializer_range": 0.02,
"layer_norm_epsilon": 1e-05,
"model_type": "venus",
"multi_query": false,
"new_decoder_architecture": false,
"num_attention_heads": 32,
"num_hidden_layers": 24,
"parallel_attn": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.27.4",
"use_cache": true,
"vocab_size": 50304,
"model_origin": "Adapted from Falcon-7B architecture (Technology by TII, Apache 2.0 License)",
"model_name": "Venus-X1"
}