|
{ |
|
"model": "falcon", |
|
"type_vocab_size": 0, |
|
"p_bias": "rotary", |
|
"rope_rank": "updown", |
|
"apply_residual_post_layernorm": false, |
|
"attention_dropout": 0.0, |
|
"bias": false, |
|
"bos_token_id": 11, |
|
"eos_token_id": 11, |
|
"hidden_dropout": 0.0, |
|
"hidden_size": 4544, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 18176, |
|
"hidden_act": "gelu", |
|
"layer_norm_eps": 1e-05, |
|
"multi_query": true, |
|
"num_attention_heads": 71, |
|
"num_hidden_layers": 32, |
|
"parallel_attn": true, |
|
"torch_dtype": "bfloat16", |
|
"multi_query_group_num": 1, |
|
"vocab_size": 65024, |
|
"skip_init": true, |
|
"norm_mode": "torch_buildin", |
|
"flash_attention": "sdpa" |
|
} |