DaryaTereshchenko
commited on
Commit
•
f8c570f
1
Parent(s):
5e147f8
Add Prism model
Browse files- config.json +34 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- prism_vocab.json +0 -0
- special_tokens_map.json +7 -0
- spm.model +3 -0
- tokenizer_config.json +50 -0
config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/dariast/prism_local/src/converted_model",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "relu",
|
5 |
+
"architectures": [
|
6 |
+
"PrismForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 0,
|
10 |
+
"d_model": 1280,
|
11 |
+
"decoder_attention_heads": 20,
|
12 |
+
"decoder_ffn_dim": 12288,
|
13 |
+
"decoder_layerdrop": 0,
|
14 |
+
"decoder_layers": 8,
|
15 |
+
"decoder_start_token_id": 2,
|
16 |
+
"dropout": 0.1,
|
17 |
+
"encoder_attention_heads": 20,
|
18 |
+
"encoder_ffn_dim": 12288,
|
19 |
+
"encoder_layerdrop": 0,
|
20 |
+
"encoder_layers": 8,
|
21 |
+
"eos_token_id": 2,
|
22 |
+
"init_std": 0.02,
|
23 |
+
"is_encoder_decoder": true,
|
24 |
+
"layernorm_embedding": false,
|
25 |
+
"max_position_embeddings": 1024,
|
26 |
+
"model_type": "prism",
|
27 |
+
"num_hidden_layers": 8,
|
28 |
+
"pad_token_id": 1,
|
29 |
+
"scale_embedding": true,
|
30 |
+
"torch_dtype": "float32",
|
31 |
+
"transformers_version": "4.43.0.dev0",
|
32 |
+
"use_cache": true,
|
33 |
+
"vocab_size": 65400
|
34 |
+
}
|
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": "4.43.0.dev0"
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d489edc8f4a63ba3374915bf71ff5073e9ebf569dc98a7d145256f1fece66c64
|
3 |
+
size 2979068832
|
prism_vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "<pad>",
|
5 |
+
"sep_token": "</s>",
|
6 |
+
"unk_token": "<unk>"
|
7 |
+
}
|
spm.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d78a6818ec4017762de5e45bc494593b3acf656d17d8063dd9772e0f0e8d257
|
3 |
+
size 1394761
|
tokenizer_config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
}
|
35 |
+
},
|
36 |
+
"additional_special_tokens": [],
|
37 |
+
"bos_token": "<s>",
|
38 |
+
"clean_up_tokenization_spaces": true,
|
39 |
+
"eos_token": "</s>",
|
40 |
+
"language_codes": "prism",
|
41 |
+
"model_max_length": 1000000000000000019884624838656,
|
42 |
+
"num_madeup_words": 8,
|
43 |
+
"pad_token": "<pad>",
|
44 |
+
"sep_token": "</s>",
|
45 |
+
"sp_model_kwargs": {},
|
46 |
+
"src_lang": "en",
|
47 |
+
"tgt_lang": "fr",
|
48 |
+
"tokenizer_class": "PrismTokenizer",
|
49 |
+
"unk_token": "<unk>"
|
50 |
+
}
|