add model
Browse files- config.json +28 -0
- pytorch_model.bin +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"XGLMForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"classifier_dropout": 0.0,
|
10 |
+
"d_model": 1024,
|
11 |
+
"decoder_attention_heads": 16,
|
12 |
+
"decoder_ffn_dim": 4096,
|
13 |
+
"decoder_layerdrop": 0.0,
|
14 |
+
"decoder_layers": 24,
|
15 |
+
"decoder_start_token_id": 2,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"encoder_layerdrop": 0.0,
|
18 |
+
"eos_token_id": 2,
|
19 |
+
"init_std": 0.02,
|
20 |
+
"max_position_embeddings": 2048,
|
21 |
+
"model_type": "xglm",
|
22 |
+
"pad_token_id": 1,
|
23 |
+
"scale_embedding": true,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.15.0.dev0",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 256008
|
28 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d5716c236039c09e444157177c11051f84f36a615105a04cb93fadf66faacbd
|
3 |
+
size 2266383929
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c49dc7e82c10227af764e518924cf2f9d50c00462750d184fa74697bba65eef8
|
3 |
+
size 4920706
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "sp_model_kwargs": {}, "tokenizer_class": "XGLMTokenizer"}
|