mcarthuradal commited on
Commit
c878d76
1 Parent(s): bb39fad

Upload T5ForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. config.json +61 -0
  3. generation_config.json +6 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -1,6 +1,7 @@
1
  ---
2
  license: apache-2.0
3
  library_name: peft
 
4
  title: Malawi
5
  emoji: 🦀
6
  colorFrom: blue
@@ -9,7 +10,6 @@ sdk: streamlit
9
  sdk_version: 1.31.0
10
  app_file: app.py
11
  pinned: false
12
- base_model: distilbert-base-uncased-finetuned-sst-2-english
13
  ---
14
 
15
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
1
  ---
2
  license: apache-2.0
3
  library_name: peft
4
+ base_model: distilbert-base-uncased-finetuned-sst-2-english
5
  title: Malawi
6
  emoji: 🦀
7
  colorFrom: blue
 
10
  sdk_version: 1.31.0
11
  app_file: app.py
12
  pinned: false
 
13
  ---
14
 
15
  Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-small",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
16
+ "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.38.1",
59
+ "use_cache": true,
60
+ "vocab_size": 32128
61
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
5
+ "transformers_version": "4.38.1"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1403ce6c6f511c985e033df130f1be952a4fa835362b0cc81f1ed9f6f53425a
3
+ size 242041896