Model saved at the end of 4 epochs
Browse files- config.json +38 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "twigs/bigbird-pegasus-large",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu_new",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"BigBirdPegasusForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"attention_type": "block_sparse",
|
| 10 |
+
"block_size": 64,
|
| 11 |
+
"bos_token_id": 2,
|
| 12 |
+
"classifier_dropout": 0.0,
|
| 13 |
+
"d_model": 1024,
|
| 14 |
+
"decoder_attention_heads": 16,
|
| 15 |
+
"decoder_ffn_dim": 4096,
|
| 16 |
+
"decoder_layerdrop": 0.0,
|
| 17 |
+
"decoder_layers": 16,
|
| 18 |
+
"decoder_start_token_id": 2,
|
| 19 |
+
"dropout": 0.1,
|
| 20 |
+
"encoder_attention_heads": 16,
|
| 21 |
+
"encoder_ffn_dim": 4096,
|
| 22 |
+
"encoder_layerdrop": 0.0,
|
| 23 |
+
"encoder_layers": 16,
|
| 24 |
+
"eos_token_id": 1,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"max_position_embeddings": 4096,
|
| 28 |
+
"model_type": "bigbird_pegasus",
|
| 29 |
+
"num_hidden_layers": 16,
|
| 30 |
+
"num_random_blocks": 3,
|
| 31 |
+
"pad_token_id": 0,
|
| 32 |
+
"scale_embedding": true,
|
| 33 |
+
"torch_dtype": "bfloat16",
|
| 34 |
+
"transformers_version": "4.25.1",
|
| 35 |
+
"use_bias": false,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 96103
|
| 38 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb3bd9e5b41cc6945ebd0f47282146e6711665f7a8a5a273bdf1d5133e9233d7
|
| 3 |
+
size 1154136109
|