Upload M2M100Encoder
Browse files- config.json +33 -33
- model.safetensors +1 -1
config.json
CHANGED
|
@@ -1,33 +1,33 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
-
"activation_dropout": 0.0,
|
| 4 |
-
"activation_function": "relu",
|
| 5 |
-
"architectures": [
|
| 6 |
-
"M2M100Encoder"
|
| 7 |
-
],
|
| 8 |
-
"attention_dropout": 0.1,
|
| 9 |
-
"bos_token_id": 0,
|
| 10 |
-
"d_model": 1024,
|
| 11 |
-
"decoder_attention_heads": 16,
|
| 12 |
-
"decoder_ffn_dim": 8192,
|
| 13 |
-
"decoder_layerdrop": 0,
|
| 14 |
-
"decoder_layers": 24,
|
| 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": 6,
|
| 21 |
-
"eos_token_id": 2,
|
| 22 |
-
"init_std": 0.02,
|
| 23 |
-
"is_encoder_decoder": true,
|
| 24 |
-
"max_position_embeddings": 1024,
|
| 25 |
-
"model_type": "m2m_100",
|
| 26 |
-
"num_hidden_layers": 6,
|
| 27 |
-
"pad_token_id": 1,
|
| 28 |
-
"scale_embedding": true,
|
| 29 |
-
"torch_dtype": "float32",
|
| 30 |
-
"transformers_version": "4.
|
| 31 |
-
"use_cache": true,
|
| 32 |
-
"vocab_size": 256206
|
| 33 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "SONAR-shallow-distilled-v1.5",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"M2M100Encoder"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"d_model": 1024,
|
| 11 |
+
"decoder_attention_heads": 16,
|
| 12 |
+
"decoder_ffn_dim": 8192,
|
| 13 |
+
"decoder_layerdrop": 0,
|
| 14 |
+
"decoder_layers": 24,
|
| 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": 6,
|
| 21 |
+
"eos_token_id": 2,
|
| 22 |
+
"init_std": 0.02,
|
| 23 |
+
"is_encoder_decoder": true,
|
| 24 |
+
"max_position_embeddings": 1024,
|
| 25 |
+
"model_type": "m2m_100",
|
| 26 |
+
"num_hidden_layers": 6,
|
| 27 |
+
"pad_token_id": 1,
|
| 28 |
+
"scale_embedding": true,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.40.0",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 256206
|
| 33 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1351747576
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7967431fb242d69fba64a5253e00ee1e7d0fc6436f2ed29c4d687df456246804
|
| 3 |
size 1351747576
|