Upload 7 files
Browse files- config.json +23 -0
- generation_config.json +8 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_function": "gelu",
|
4 |
+
"attention_dropout": 0.1,
|
5 |
+
"attention_heads": 16,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"d_model": 2048,
|
8 |
+
"decoder_start_token_id": 2,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"ffn_dim": 8192,
|
12 |
+
"init_std": 0.02,
|
13 |
+
"layerdrop": 0.0,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"model_type": "xglm",
|
16 |
+
"num_layers": 24,
|
17 |
+
"pad_token_id": 1,
|
18 |
+
"scale_embedding": true,
|
19 |
+
"torch_dtype": "float16",
|
20 |
+
"transformers_version": "4.29.0",
|
21 |
+
"use_cache": true,
|
22 |
+
"vocab_size": 50335
|
23 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"pad_token_id": 1,
|
7 |
+
"transformers_version": "4.29.0"
|
8 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:782ba2ef9c79b768ce318e14398eee0b56a1e20aec742b2d034c3e1e9f5d4cd5
|
3 |
+
size 2623502651
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "sp_model_kwargs": {}, "vocab_type": "spm"}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|