Hugging Face's logo

101rakibulhasan
/
extendedBanglaT5

Translation
Safetensors
Bengali
English
t5
bangla
bengali
classification
seq2seq
text2text-generation
Model card Files
xet
 Community
101rakibulhasan commited on
Commit
fa98226
·
verified ·
1 Parent(s): 56b082f

Model checkpoint at step 26400

Browse files
Files changed (3) hide show
  1. config.json +32 -32
  2. generation_config.json +9 -9
  3. model.safetensors +1 -1
config.json CHANGED
@@ -1,32 +1,32 @@
1
- {
2
- "architectures": [
3
- "T5ForConditionalGeneration"
4
- ],
5
- "classifier_dropout": 0.0,
6
- "d_ff": 2048,
7
- "d_kv": 64,
8
- "d_model": 768,
9
- "decoder_start_token_id": 0,
10
- "dense_act_fn": "gelu_new",
11
- "dropout_rate": 0.1,
12
- "dtype": "float32",
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
- "gradient_checkpointing": false,
16
- "initializer_factor": 1.0,
17
- "is_encoder_decoder": true,
18
- "is_gated_act": true,
19
- "layer_norm_epsilon": 1e-06,
20
- "model_type": "t5",
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,
27
- "relative_attention_num_buckets": 32,
28
- "tie_word_embeddings": false,
29
- "transformers_version": "4.56.0",
30
- "use_cache": true,
31
- "vocab_size": 53963
32
- }
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "dtype": "float32",
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
15
+ "gradient_checkpointing": false,
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
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,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
+ "transformers_version": "4.56.1",
30
+ "use_cache": true,
31
+ "vocab_size": 53963
32
+ }
generation_config.json CHANGED
@@ -1,9 +1,9 @@
1
- {
2
- "_from_model_config": true,
3
- "decoder_start_token_id": 0,
4
- "eos_token_id": [
5
- 1
6
- ],
7
- "pad_token_id": 0,
8
- "transformers_version": "4.56.0"
9
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": [
5
+ 1
6
+ ],
7
+ "pad_token_id": 0,
8
+ "transformers_version": "4.56.1"
9
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f842dce7b29caa92734ebae2f55491114c1de08ac5f14767f3f194703c8991a
3
  size 1124499304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9373522cd23da6a035d3e3eabc61a241f70bca72a57e0d4e9546101c3b23036
3
  size 1124499304