Hugging Face's logo

Sujithanumala
/
QuizBot.AI-base

Transformers
PyTorch
TensorBoard
t5
text2text-generation
text-generation-inference
Model card Files
xet
Metrics Community
1
Sujithanumala commited on
Commit
2b23008
·
1 Parent(s): 265a14a

Training in progress, step 500

Browse files
Files changed (8) hide show
  1. config.json +6 -6
  2. pytorch_model.bin +2 -2
  3. runs/Feb16_05-59-40_1dc85b725701/1708063393.168579/events.out.tfevents.1708063393.1dc85b725701.207.1 +3 -0
  4. runs/Feb16_05-59-40_1dc85b725701/events.out.tfevents.1708063393.1dc85b725701.207.0 +3 -0
  5. spiece.model +3 -0
  6. tokenizer.json +1 -6
  7. tokenizer_config.json +1 -0
  8. training_args.bin +1 -1
config.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "_name_or_path": "t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
- "d_ff": 3072,
7
  "d_kv": 64,
8
- "d_model": 768,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "relu",
11
  "dropout": 0.2,
@@ -18,9 +18,9 @@
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
- "num_decoder_layers": 12,
22
- "num_heads": 12,
23
- "num_layers": 12,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
 
1
  {
2
+ "_name_or_path": "Sujithanumala/QuizBot.AI-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
+ "d_ff": 2048,
7
  "d_kv": 64,
8
+ "d_model": 512,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "relu",
11
  "dropout": 0.2,
 
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,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16c6e9610aef6f4a103bd1f3122dd60ceb1812f7df967a8d54fde23722b7cb6b
3
- size 891702929
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ba214dce678e2b67effb47752ba065cca67d6d6de2b1b44b9957603cfd7237d
3
+ size 242071641
runs/Feb16_05-59-40_1dc85b725701/1708063393.168579/events.out.tfevents.1708063393.1dc85b725701.207.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094816387c8b199be289ed7e91522286ae308a439ef8dac25eac822071c10195
3
+ size 6046
runs/Feb16_05-59-40_1dc85b725701/events.out.tfevents.1708063393.1dc85b725701.207.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07b8ae743a85586724a6fdfb87d9be53d8e45e55ce1efa9471de5f3f6c90a72f
3
+ size 4951
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 512,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
tokenizer_config.json CHANGED
@@ -101,6 +101,7 @@
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
 
104
  "eos_token": "</s>",
105
  "extra_ids": 100,
106
  "model_max_length": 512,
 
101
  "<extra_id_98>",
102
  "<extra_id_99>"
103
  ],
104
+ "clean_up_tokenization_spaces": true,
105
  "eos_token": "</s>",
106
  "extra_ids": 100,
107
  "model_max_length": 512,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:154685cd1fb246e6961ba14130ea1451f1880faa446cb7a0b39983ee938d8aed
3
  size 3707
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b5a74f3fdb892c2a9e3e5071f8bcbab98b38fb9b4065f29bd0223049ff01e5d
3
  size 3707