Commit
•
20e9d77
1
Parent(s):
7bd9638
add model
Browse files- config.json +28 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/content/drive/MyDrive/byt5-small/models/e3_lr0.0001",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 3584,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1472,
|
| 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": 4,
|
| 18 |
+
"num_heads": 6,
|
| 19 |
+
"num_layers": 12,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"relative_attention_num_buckets": 32,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.12.5",
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"vocab_size": 384
|
| 28 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ac8cfac6e0aab2b20064a64fcc2b84b6d3ea84570c1c2362e66c9eb0d2c5af5
|
| 3 |
+
size 1198625069
|