Commit From AutoTrain
Browse files- .gitattributes +3 -0
- README.md +24 -0
- config.json +65 -0
- pytorch_model.bin +3 -0
- source.spm +0 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer_config.json +13 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -32,3 +32,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- translation
|
5 |
+
language:
|
6 |
+
- unk
|
7 |
+
- unk
|
8 |
+
datasets:
|
9 |
+
- zhaozh/autotrain-data-chatdoctor-reft-en-zh
|
10 |
+
co2_eq_emissions:
|
11 |
+
emissions: 2.240193635056679
|
12 |
+
---
|
13 |
+
|
14 |
+
# Model Trained Using AutoTrain
|
15 |
+
|
16 |
+
- Problem type: Translation
|
17 |
+
- Model ID: 45173113346
|
18 |
+
- CO2 Emissions (in grams): 2.2402
|
19 |
+
|
20 |
+
## Validation Metrics
|
21 |
+
|
22 |
+
- Loss: 1.636
|
23 |
+
- SacreBLEU: 29.513
|
24 |
+
- Gen len: 176.613
|
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "AutoTrain",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "swish",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"MarianMTModel"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bad_words_ids": [
|
12 |
+
[
|
13 |
+
65000
|
14 |
+
]
|
15 |
+
],
|
16 |
+
"bos_token_id": 0,
|
17 |
+
"classif_dropout": 0.0,
|
18 |
+
"classifier_dropout": 0.0,
|
19 |
+
"d_model": 512,
|
20 |
+
"decoder_attention_heads": 8,
|
21 |
+
"decoder_ffn_dim": 2048,
|
22 |
+
"decoder_layerdrop": 0.0,
|
23 |
+
"decoder_layers": 6,
|
24 |
+
"decoder_start_token_id": 65000,
|
25 |
+
"decoder_vocab_size": 65001,
|
26 |
+
"do_blenderbot_90_layernorm": false,
|
27 |
+
"dropout": 0.1,
|
28 |
+
"encoder_attention_heads": 8,
|
29 |
+
"encoder_ffn_dim": 2048,
|
30 |
+
"encoder_layerdrop": 0.0,
|
31 |
+
"encoder_layers": 6,
|
32 |
+
"eos_token_id": 0,
|
33 |
+
"extra_pos_embeddings": 0,
|
34 |
+
"force_bos_token_to_be_generated": false,
|
35 |
+
"forced_eos_token_id": 0,
|
36 |
+
"gradient_checkpointing": false,
|
37 |
+
"id2label": {
|
38 |
+
"0": "LABEL_0",
|
39 |
+
"1": "LABEL_1",
|
40 |
+
"2": "LABEL_2"
|
41 |
+
},
|
42 |
+
"init_std": 0.02,
|
43 |
+
"is_encoder_decoder": true,
|
44 |
+
"label2id": {
|
45 |
+
"LABEL_0": 0,
|
46 |
+
"LABEL_1": 1,
|
47 |
+
"LABEL_2": 2
|
48 |
+
},
|
49 |
+
"max_length": 256,
|
50 |
+
"max_position_embeddings": 512,
|
51 |
+
"model_type": "marian",
|
52 |
+
"normalize_before": false,
|
53 |
+
"normalize_embedding": false,
|
54 |
+
"num_beams": 4,
|
55 |
+
"num_hidden_layers": 6,
|
56 |
+
"pad_token_id": 65000,
|
57 |
+
"padding": "max_length",
|
58 |
+
"scale_embedding": true,
|
59 |
+
"share_encoder_decoder_embeddings": true,
|
60 |
+
"static_position_embeddings": true,
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.25.1",
|
63 |
+
"use_cache": true,
|
64 |
+
"vocab_size": 65001
|
65 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e48be372f0196b4305ec6bbdbf4667c6d02070b8ed07f6ec34848df9288c923
|
3 |
+
size 310022533
|
source.spm
ADDED
Binary file (806 kB). View file
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
target.spm
ADDED
Binary file (805 kB). View file
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"model_max_length": 512,
|
4 |
+
"name_or_path": "AutoTrain",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"separate_vocabs": false,
|
7 |
+
"source_lang": "eng",
|
8 |
+
"sp_model_kwargs": {},
|
9 |
+
"special_tokens_map_file": null,
|
10 |
+
"target_lang": "zho",
|
11 |
+
"tokenizer_class": "MarianTokenizer",
|
12 |
+
"unk_token": "<unk>"
|
13 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|