|
{ |
|
"alibi": true, |
|
"architectures": [ |
|
"FalconForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bias": false, |
|
"bos_token_id": 11, |
|
"eos_token_id": 11, |
|
"hidden_dropout": 0.0, |
|
"hidden_size": 64, |
|
"initializer_range": 0.02, |
|
"layer_norm_epsilon": 1e-05, |
|
"model_type": "falcon", |
|
"multi_query": true, |
|
"new_decoder_architecture": true, |
|
"num_attention_heads": 4, |
|
"num_hidden_layers": 2, |
|
"num_kv_heads": 2, |
|
"parallel_attn": true, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.31.0.dev0", |
|
"use_cache": true, |
|
"vocab_size": 1024 |
|
} |
|
|