Upload M2M100ForConditionalGeneration
Browse files- config.json +7 -30
- generation_config.json +0 -3
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,56 +1,33 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/
|
| 3 |
-
"_num_labels": 3,
|
| 4 |
"activation_dropout": 0.0,
|
| 5 |
"activation_function": "relu",
|
| 6 |
-
"add_bias_logits": false,
|
| 7 |
-
"add_final_layer_norm": true,
|
| 8 |
"architectures": [
|
| 9 |
-
"
|
| 10 |
],
|
| 11 |
-
"attention_dropout": 0.
|
| 12 |
"bos_token_id": 0,
|
| 13 |
-
"classif_dropout": 0.0,
|
| 14 |
-
"classifier_dropout": 0.0,
|
| 15 |
"d_model": 1024,
|
| 16 |
"decoder_attention_heads": 16,
|
| 17 |
"decoder_ffn_dim": 4096,
|
| 18 |
-
"decoder_layerdrop": 0
|
| 19 |
"decoder_layers": 12,
|
| 20 |
"decoder_start_token_id": 2,
|
| 21 |
"dropout": 0.1,
|
| 22 |
-
"early_stopping": true,
|
| 23 |
"encoder_attention_heads": 16,
|
| 24 |
"encoder_ffn_dim": 4096,
|
| 25 |
-
"encoder_layerdrop": 0
|
| 26 |
"encoder_layers": 12,
|
| 27 |
"eos_token_id": 2,
|
| 28 |
-
"forced_eos_token_id": 2,
|
| 29 |
-
"gradient_checkpointing": false,
|
| 30 |
-
"id2label": {
|
| 31 |
-
"0": "LABEL_0",
|
| 32 |
-
"1": "LABEL_1",
|
| 33 |
-
"2": "LABEL_2"
|
| 34 |
-
},
|
| 35 |
"init_std": 0.02,
|
| 36 |
"is_encoder_decoder": true,
|
| 37 |
-
"label2id": {
|
| 38 |
-
"LABEL_0": 0,
|
| 39 |
-
"LABEL_1": 1,
|
| 40 |
-
"LABEL_2": 2
|
| 41 |
-
},
|
| 42 |
"max_length": 200,
|
| 43 |
"max_position_embeddings": 1024,
|
| 44 |
-
"model_type": "
|
| 45 |
-
"normalize_before": true,
|
| 46 |
-
"normalize_embedding": true,
|
| 47 |
-
"num_beams": 5,
|
| 48 |
"num_hidden_layers": 12,
|
| 49 |
-
"output_past": true,
|
| 50 |
"pad_token_id": 1,
|
| 51 |
"scale_embedding": true,
|
| 52 |
-
"
|
| 53 |
-
"tokenizer_class": "MBart50Tokenizer",
|
| 54 |
"torch_dtype": "float32",
|
| 55 |
"transformers_version": "4.33.0",
|
| 56 |
"use_cache": true,
|
|
|
|
| 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": "4.33.0",
|
| 33 |
"use_cache": true,
|
generation_config.json
CHANGED
|
@@ -2,11 +2,8 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 0,
|
| 4 |
"decoder_start_token_id": 2,
|
| 5 |
-
"early_stopping": true,
|
| 6 |
"eos_token_id": 2,
|
| 7 |
-
"forced_eos_token_id": 2,
|
| 8 |
"max_length": 200,
|
| 9 |
-
"num_beams": 5,
|
| 10 |
"pad_token_id": 1,
|
| 11 |
"transformers_version": "4.33.0"
|
| 12 |
}
|
|
|
|
| 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": "4.33.0"
|
| 9 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6eecb7ced59378a4aaaddf17014dcd66e3058e2278d6e286301582421261eaa
|
| 3 |
+
size 2460465086
|