DReaper commited on
Commit
20e0ed3
·
verified ·
1 Parent(s): 30e5917

Upload T5ForConditionalGeneration

Browse files
Files changed (2) hide show
  1. config.json +6 -37
  2. model.safetensors +2 -2
config.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
- "_name_or_path": "DReaper/ecommerce-intent-classifier",
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,
@@ -17,43 +17,12 @@
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": 4,
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": "float16",
58
  "transformers_version": "4.47.1",
59
  "use_cache": true,
 
1
  {
2
+ "_name_or_path": "D:\\Development\\PycharmProjects\\BookingChatbot\\models/t5_distil_intent_classifier_model",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
+ "d_ff": 512,
8
  "d_kv": 64,
9
+ "d_model": 128,
10
  "decoder_start_token_id": 0,
11
  "dense_act_fn": "relu",
12
  "dropout_rate": 0.1,
 
17
  "is_gated_act": false,
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
+ "num_decoder_layers": 3,
21
+ "num_heads": 2,
22
+ "num_layers": 3,
 
 
23
  "pad_token_id": 0,
24
  "relative_attention_max_distance": 128,
25
  "relative_attention_num_buckets": 32,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  "torch_dtype": "float16",
27
  "transformers_version": "4.47.1",
28
  "use_cache": true,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:675c26e9d3d253adf9c376e4218eed44a0cb6f77119cf0b058dc3740dc33d8a1
3
- size 108439656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d65e92624642699d481a20d9b06beb7e17ce373a5a02b2fbd70600cdabbbfb49
3
+ size 10989640