multi-train commited on
Commit
2400f9e
1 Parent(s): 62ae72d

Upload 9 files

Browse files
Files changed (3) hide show
  1. config.json +59 -8
  2. pytorch_model.bin +1 -1
  3. tokenizer_config.json +1 -1
config.json CHANGED
@@ -1,9 +1,60 @@
1
  {
2
- "word_embedding_dimension": 768,
3
- "pooling_mode_cls_token": false,
4
- "pooling_mode_mean_tokens": true,
5
- "pooling_mode_max_tokens": false,
6
- "pooling_mode_mean_sqrt_len_tokens": false,
7
- "pooling_mode_weightedmean_tokens": false,
8
- "pooling_mode_lasttoken": false
9
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "_name_or_path": "/home2/huggingface/outputs/xl_30000_fever/checkpoint-300/",
3
+ "architectures": [
4
+ "T5EncoderModel"
5
+ ],
6
+ "d_ff": 16384,
7
+ "d_kv": 128,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 24,
21
+ "num_heads": 32,
22
+ "num_layers": 24,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.20.0.dev0",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:904227ee22ccbd02b0a60a5040ee49bde055892fd0f663ac43397f003dbab34b
3
  size 4963705019
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b065dd74cb4423b155cada6ebf11f97cdcb67b2f10841a8a810d674b10bbf99
3
  size 4963705019
tokenizer_config.json CHANGED
@@ -104,7 +104,7 @@
104
  "eos_token": "</s>",
105
  "extra_ids": 100,
106
  "model_max_length": 512,
107
- "name_or_path": "sentence-transformers/gtr-t5-xl",
108
  "pad_token": "<pad>",
109
  "special_tokens_map_file": null,
110
  "tokenizer_class": "T5Tokenizer",
104
  "eos_token": "</s>",
105
  "extra_ids": 100,
106
  "model_max_length": 512,
107
+ "name_or_path": "/home2/huggingface/outputs/xl_30000_fever/checkpoint-300",
108
  "pad_token": "<pad>",
109
  "special_tokens_map_file": null,
110
  "tokenizer_class": "T5Tokenizer",