Upload FSMTForConditionalGeneration
#11
by
hf-transformers-bot
- opened
- .gitattributes +1 -0
- README.md +1 -1
- config.json +31 -22
- generation_config.json +1 -1
- model.safetensors +3 -0
.gitattributes
CHANGED
@@ -6,3 +6,4 @@
|
|
6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
|
|
|
6 |
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
+
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
- en
|
4 |
- de
|
5 |
tags:
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
- en
|
4 |
- de
|
5 |
tags:
|
config.json
CHANGED
@@ -1,37 +1,46 @@
|
|
1 |
{
|
|
|
|
|
2 |
"architectures": [
|
3 |
"FSMTForConditionalGeneration"
|
4 |
],
|
5 |
-
"model_type": "fsmt",
|
6 |
-
"activation_dropout": 0.0,
|
7 |
-
"activation_function": "relu",
|
8 |
"attention_dropout": 0.1,
|
|
|
9 |
"d_model": 1024,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"dropout": 0.2,
|
11 |
-
"init_std": 0.02,
|
12 |
-
"max_position_embeddings": 1024,
|
13 |
-
"num_hidden_layers": 6,
|
14 |
-
"src_vocab_size": 42024,
|
15 |
-
"tgt_vocab_size": 42024,
|
16 |
-
"langs": [
|
17 |
-
"en",
|
18 |
-
"de"
|
19 |
-
],
|
20 |
"encoder_attention_heads": 16,
|
21 |
"encoder_ffn_dim": 8192,
|
22 |
"encoder_layerdrop": 0,
|
23 |
"encoder_layers": 6,
|
24 |
-
"decoder_attention_heads": 16,
|
25 |
-
"decoder_ffn_dim": 4096,
|
26 |
-
"decoder_layerdrop": 0,
|
27 |
-
"decoder_layers": 6,
|
28 |
-
"bos_token_id": 0,
|
29 |
-
"pad_token_id": 1,
|
30 |
"eos_token_id": 2,
|
|
|
|
|
31 |
"is_encoder_decoder": true,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
"scale_embedding": true,
|
|
|
|
|
33 |
"tie_word_embeddings": true,
|
34 |
-
"
|
35 |
-
"
|
36 |
-
"
|
37 |
-
}
|
|
|
1 |
{
|
2 |
+
"activation_dropout": 0.0,
|
3 |
+
"activation_function": "relu",
|
4 |
"architectures": [
|
5 |
"FSMTForConditionalGeneration"
|
6 |
],
|
|
|
|
|
|
|
7 |
"attention_dropout": 0.1,
|
8 |
+
"bos_token_id": 0,
|
9 |
"d_model": 1024,
|
10 |
+
"decoder": {
|
11 |
+
"bos_token_id": 2,
|
12 |
+
"model_type": "fsmt_decoder",
|
13 |
+
"vocab_size": 42024
|
14 |
+
},
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
"dropout": 0.2,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
21 |
"encoder_attention_heads": 16,
|
22 |
"encoder_ffn_dim": 8192,
|
23 |
"encoder_layerdrop": 0,
|
24 |
"encoder_layers": 6,
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
"eos_token_id": 2,
|
26 |
+
"forced_eos_token_id": 2,
|
27 |
+
"init_std": 0.02,
|
28 |
"is_encoder_decoder": true,
|
29 |
+
"langs": [
|
30 |
+
"en",
|
31 |
+
"de"
|
32 |
+
],
|
33 |
+
"max_length": 200,
|
34 |
+
"max_position_embeddings": 1024,
|
35 |
+
"model_type": "fsmt",
|
36 |
+
"num_beams": 5,
|
37 |
+
"num_hidden_layers": 6,
|
38 |
+
"pad_token_id": 1,
|
39 |
"scale_embedding": true,
|
40 |
+
"src_vocab_size": 42024,
|
41 |
+
"tgt_vocab_size": 42024,
|
42 |
"tie_word_embeddings": true,
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.53.0.dev0",
|
45 |
+
"use_cache": true
|
46 |
+
}
|
generation_config.json
CHANGED
@@ -7,5 +7,5 @@
|
|
7 |
"max_length": 200,
|
8 |
"num_beams": 5,
|
9 |
"pad_token_id": 1,
|
10 |
-
"transformers_version": "4.
|
11 |
}
|
|
|
7 |
"max_length": 200,
|
8 |
"num_beams": 5,
|
9 |
"pad_token_id": 1,
|
10 |
+
"transformers_version": "4.53.0.dev0"
|
11 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12e5a6c31b372d402c92c5bc39d060ec3e7a52ec93f2d28fbec7135bb56905f0
|
3 |
+
size 1087419504
|