falcon-rw-1b / config.json
Daniel Hesslow
Upload RWForCausalLM
e881e96
raw
history blame
665 Bytes
{
"alibi": true,
"apply_residual_connection_post_layernorm": false,
"architectures": [
"RWForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_RW.RWConfig",
"AutoModelForCausalLM": "modelling_RW.RWForCausalLM"
},
"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": "RefinedWebModel",
"multi_query": false,
"n_head": 32,
"n_layer": 24,
"parallel_attn": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.27.4",
"use_cache": true,
"vocab_size": 50304
}