28 lines
675 B
JSON
28 lines
675 B
JSON
{
|
|
"_name_or_path": "./converted_repos/falcon-rw-1b",
|
|
"alibi": true,
|
|
"apply_residual_connection_post_layernorm": false,
|
|
"architectures": [
|
|
"FalconForCausalLM"
|
|
],
|
|
"attention_dropout": 0.0,
|
|
"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": "falcon",
|
|
"multi_query": false,
|
|
"num_attention_heads": 32,
|
|
"num_kv_heads": 32,
|
|
"num_hidden_layers": 24,
|
|
"new_decoder_architecture": false,
|
|
"parallel_attn": false,
|
|
"torch_dtype": "bfloat16",
|
|
"transformers_version": "4.31.0.dev0",
|
|
"use_cache": true,
|
|
"vocab_size": 50304
|
|
}
|