Hugging Face's logo

vikp
/
donut-decoder

Text Generation
Transformers
Safetensors
mbart
Inference Endpoints
Model card Files Community
vikp commited on
Commit
dfc8cd4
•
1 Parent(s): cf7dfd7

Upload MBartForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +26 -24
  2. generation_config.json +4 -3
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,34 +1,36 @@
1
  {
2
- "_name_or_path": "google/byt5-small",
 
 
 
3
  "architectures": [
4
- "T5ForCausalLM"
5
  ],
 
 
6
  "classifier_dropout": 0.0,
7
- "d_ff": 3584,
8
- "d_kv": 64,
9
- "d_model": 1472,
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
- "gradient_checkpointing": false,
16
- "initializer_factor": 1.0,
 
 
 
17
  "is_decoder": true,
18
  "is_encoder_decoder": false,
19
- "is_gated_act": true,
20
- "layer_norm_epsilon": 1e-06,
21
- "model_type": "t5",
22
- "num_decoder_layers": 6,
23
- "num_heads": 6,
24
- "num_layers": 12,
25
- "pad_token_id": 0,
26
- "relative_attention_max_distance": 128,
27
- "relative_attention_num_buckets": 32,
28
- "tie_word_embeddings": false,
29
- "tokenizer_class": "ByT5Tokenizer",
30
  "torch_dtype": "float32",
31
  "transformers_version": "4.36.2",
32
  "use_cache": true,
33
- "vocab_size": 384
34
  }
 
1
  {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "add_cross_attention": true,
5
+ "add_final_layer_norm": true,
6
  "architectures": [
7
+ "MBartForCausalLM"
8
  ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 0,
11
  "classifier_dropout": 0.0,
12
+ "d_model": 1024,
13
+ "decoder_attention_heads": 16,
14
+ "decoder_ffn_dim": 4096,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 4,
17
+ "dropout": 0.1,
18
+ "encoder_attention_heads": 16,
19
+ "encoder_ffn_dim": 4096,
20
+ "encoder_layerdrop": 0.0,
21
+ "encoder_layers": 12,
22
+ "eos_token_id": 2,
23
+ "forced_eos_token_id": 2,
24
+ "init_std": 0.02,
25
  "is_decoder": true,
26
  "is_encoder_decoder": false,
27
+ "max_position_embeddings": 1536,
28
+ "model_type": "mbart",
29
+ "num_hidden_layers": 12,
30
+ "pad_token_id": 1,
31
+ "scale_embedding": true,
 
 
 
 
 
 
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.36.2",
34
  "use_cache": true,
35
+ "vocab_size": 57525
36
  }
generation_config.json CHANGED
@@ -1,7 +1,8 @@
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": "4.36.2"
7
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 1,
7
  "transformers_version": "4.36.2"
8
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5473d69b4c294d4dca795464019b94eebae05a5a81fa95510de390a51d42c9b
3
- size 493019416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85811bbbb4f4e11e3bb6d0841574c6eca112884c71e2a70ea81bc7d782677260
3
+ size 510698128