bread null
commited on
Commit
•
713d3ea
1
Parent(s):
22ad659
Initial commit
Browse files- config.json +32 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"BigBirdForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"attention_type": "block_sparse",
|
| 7 |
+
"block_size": 64,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"classifier_dropout": null,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"hidden_act": "gelu_new",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1536,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"is_decoder": true,
|
| 17 |
+
"layer_norm_eps": 1e-12,
|
| 18 |
+
"max_position_embeddings": 4096,
|
| 19 |
+
"model_type": "big_bird",
|
| 20 |
+
"num_attention_heads": 24,
|
| 21 |
+
"num_hidden_layers": 72,
|
| 22 |
+
"num_random_blocks": 5,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"rescale_embeddings": false,
|
| 25 |
+
"sep_token_id": 66,
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.30.2",
|
| 28 |
+
"type_vocab_size": 2,
|
| 29 |
+
"use_bias": true,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 50304
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.30.2"
|
| 7 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0f666a8fe4a8676ec4ed093dd255f02481396dacd3a1311fe51f295f8ec3f8b
|
| 3 |
+
size 5794463166
|