b0ba4f0eba680f009b8720b25f99776ed0d72e5635499f9b4dd2548c73a4375a
Browse files- config.json +9 -2
config.json
CHANGED
|
@@ -1,17 +1,20 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
|
|
|
| 6 |
"d_ff": 10240,
|
| 7 |
"d_kv": 64,
|
| 8 |
"d_model": 4096,
|
| 9 |
"decoder_start_token_id": 0,
|
|
|
|
| 10 |
"dropout_rate": 0.1,
|
| 11 |
"eos_token_id": 1,
|
| 12 |
"feed_forward_proj": "gated-gelu",
|
| 13 |
"initializer_factor": 1.0,
|
| 14 |
"is_encoder_decoder": true,
|
|
|
|
| 15 |
"layer_norm_epsilon": 1e-06,
|
| 16 |
"model_type": "t5",
|
| 17 |
"num_decoder_layers": 24,
|
|
@@ -19,7 +22,11 @@
|
|
| 19 |
"num_layers": 24,
|
| 20 |
"output_past": true,
|
| 21 |
"pad_token_id": 0,
|
|
|
|
| 22 |
"relative_attention_num_buckets": 32,
|
| 23 |
"tie_word_embeddings": false,
|
|
|
|
|
|
|
|
|
|
| 24 |
"vocab_size": 32128
|
| 25 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "mcmonkey/google_t5-v1_1-xxl_encoderonly",
|
| 3 |
"architectures": [
|
| 4 |
+
"T5EncoderModel"
|
| 5 |
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
"d_ff": 10240,
|
| 8 |
"d_kv": 64,
|
| 9 |
"d_model": 4096,
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
"dropout_rate": 0.1,
|
| 13 |
"eos_token_id": 1,
|
| 14 |
"feed_forward_proj": "gated-gelu",
|
| 15 |
"initializer_factor": 1.0,
|
| 16 |
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
"layer_norm_epsilon": 1e-06,
|
| 19 |
"model_type": "t5",
|
| 20 |
"num_decoder_layers": 24,
|
|
|
|
| 22 |
"num_layers": 24,
|
| 23 |
"output_past": true,
|
| 24 |
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
"relative_attention_num_buckets": 32,
|
| 27 |
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "bfloat16",
|
| 29 |
+
"transformers_version": "4.44.2",
|
| 30 |
+
"use_cache": true,
|
| 31 |
"vocab_size": 32128
|
| 32 |
}
|