Hugging Face's logo

Edgar404
/
t5_small_default

Transformers
PyTorch
m2m_100
text2text-generation
Model card Files
xet
Community
Edgar404 commited on
Commit
e5609e8
·
verified ·
1 Parent(s): b3fcd5c

Training in progress, epoch 0

Browse files
Files changed (3) hide show
  1. config.json +28 -26
  2. generation_config.json +6 -4
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,33 +1,35 @@
1
  {
2
- "_name_or_path": "google/mt5-base",
 
 
3
  "architectures": [
4
- "T5ForConditionalGeneration"
5
  ],
6
- "classifier_dropout": 0.0,
7
- "d_ff": 2048,
8
- "d_kv": 64,
9
- "d_model": 768,
10
- "decoder_start_token_id": 0,
11
- "dense_act_fn": "gelu_new",
12
- "dropout_rate": 0.1,
13
- "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
- "initializer_factor": 1.0,
 
 
 
 
 
16
  "is_encoder_decoder": true,
17
- "is_gated_act": true,
18
- "layer_norm_epsilon": 1e-06,
19
- "model_type": "t5",
20
- "num_decoder_layers": 12,
21
- "num_heads": 12,
22
- "num_layers": 12,
23
- "output_past": true,
24
- "pad_token_id": 0,
25
- "relative_attention_max_distance": 128,
26
- "relative_attention_num_buckets": 32,
27
- "tie_word_embeddings": false,
28
- "tokenizer_class": "T5Tokenizer",
29
  "torch_dtype": "float32",
30
- "transformers_version": "4.42.3",
31
  "use_cache": true,
32
- "vocab_size": 250112
33
  }
 
1
  {
2
+ "_name_or_path": "facebook/nllb-200-distilled-600M",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "relu",
5
  "architectures": [
6
+ "M2M100ForConditionalGeneration"
7
  ],
8
+ "attention_dropout": 0.1,
9
+ "bos_token_id": 0,
10
+ "d_model": 1024,
11
+ "decoder_attention_heads": 16,
12
+ "decoder_ffn_dim": 4096,
13
+ "decoder_layerdrop": 0,
14
+ "decoder_layers": 12,
15
+ "decoder_start_token_id": 2,
16
+ "dropout": 0.1,
17
+ "encoder_attention_heads": 16,
18
+ "encoder_ffn_dim": 4096,
19
+ "encoder_layerdrop": 0,
20
+ "encoder_layers": 12,
21
+ "eos_token_id": 2,
22
+ "init_std": 0.02,
23
  "is_encoder_decoder": true,
24
+ "max_length": 200,
25
+ "max_position_embeddings": 1024,
26
+ "model_type": "m2m_100",
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 1,
29
+ "scale_embedding": true,
30
+ "tokenizer_class": "NllbTokenizer",
 
 
 
 
 
31
  "torch_dtype": "float32",
32
+ "transformers_version": "4.44.0",
33
  "use_cache": true,
34
+ "vocab_size": 256206
35
  }
generation_config.json CHANGED
@@ -1,7 +1,9 @@
1
  {
2
  "_from_model_config": true,
3
- "decoder_start_token_id": 0,
4
- "eos_token_id": 1,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.42.3"
 
 
7
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "max_length": 200,
7
+ "pad_token_id": 1,
8
+ "transformers_version": "4.44.0"
9
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bfde211fe13af145d823800ba26372babbfbf70c462508f3d3047eb2631f9df
3
- size 2329703026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a9351fda7519843a4972eb9b90fba170c07830d5c90053e104525cab62732c
3
+ size 2460469182