Update checkpoint for transformers>=4.29
#17
by
ArthurZ
HF Staff
- opened
- config.json +8 -8
- generation_config.json +6 -6
- model.safetensors +2 -2
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bad_words_ids": [
|
| 9 |
[
|
| 10 |
-
|
| 11 |
]
|
| 12 |
],
|
| 13 |
"bos_token_id": 0,
|
|
@@ -17,29 +17,29 @@
|
|
| 17 |
"decoder_ffn_dim": 4096,
|
| 18 |
"decoder_layerdrop": 0.0,
|
| 19 |
"decoder_layers": 6,
|
| 20 |
-
"decoder_start_token_id":
|
| 21 |
-
"decoder_vocab_size":
|
| 22 |
"dropout": 0.1,
|
| 23 |
"encoder_attention_heads": 16,
|
| 24 |
"encoder_ffn_dim": 4096,
|
| 25 |
"encoder_layerdrop": 0.0,
|
| 26 |
"encoder_layers": 6,
|
| 27 |
-
"eos_token_id":
|
| 28 |
-
"forced_eos_token_id":
|
| 29 |
"init_std": 0.02,
|
| 30 |
"is_encoder_decoder": true,
|
| 31 |
"max_length": 512,
|
| 32 |
"max_position_embeddings": 1024,
|
| 33 |
"model_type": "marian",
|
| 34 |
"normalize_embedding": false,
|
| 35 |
-
"num_beams":
|
| 36 |
"num_hidden_layers": 6,
|
| 37 |
-
"pad_token_id":
|
| 38 |
"scale_embedding": true,
|
| 39 |
"share_encoder_decoder_embeddings": true,
|
| 40 |
"static_position_embeddings": true,
|
| 41 |
"torch_dtype": "float16",
|
| 42 |
"transformers_version": "4.34.0.dev0",
|
| 43 |
"use_cache": true,
|
| 44 |
-
"vocab_size":
|
| 45 |
}
|
|
|
|
| 7 |
"attention_dropout": 0.0,
|
| 8 |
"bad_words_ids": [
|
| 9 |
[
|
| 10 |
+
57829
|
| 11 |
]
|
| 12 |
],
|
| 13 |
"bos_token_id": 0,
|
|
|
|
| 17 |
"decoder_ffn_dim": 4096,
|
| 18 |
"decoder_layerdrop": 0.0,
|
| 19 |
"decoder_layers": 6,
|
| 20 |
+
"decoder_start_token_id": 57829,
|
| 21 |
+
"decoder_vocab_size": 57830,
|
| 22 |
"dropout": 0.1,
|
| 23 |
"encoder_attention_heads": 16,
|
| 24 |
"encoder_ffn_dim": 4096,
|
| 25 |
"encoder_layerdrop": 0.0,
|
| 26 |
"encoder_layers": 6,
|
| 27 |
+
"eos_token_id": 41756,
|
| 28 |
+
"forced_eos_token_id": 41756,
|
| 29 |
"init_std": 0.02,
|
| 30 |
"is_encoder_decoder": true,
|
| 31 |
"max_length": 512,
|
| 32 |
"max_position_embeddings": 1024,
|
| 33 |
"model_type": "marian",
|
| 34 |
"normalize_embedding": false,
|
| 35 |
+
"num_beams": 6,
|
| 36 |
"num_hidden_layers": 6,
|
| 37 |
+
"pad_token_id": 57829,
|
| 38 |
"scale_embedding": true,
|
| 39 |
"share_encoder_decoder_embeddings": true,
|
| 40 |
"static_position_embeddings": true,
|
| 41 |
"torch_dtype": "float16",
|
| 42 |
"transformers_version": "4.34.0.dev0",
|
| 43 |
"use_cache": true,
|
| 44 |
+
"vocab_size": 57830
|
| 45 |
}
|
generation_config.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
"bad_words_ids": [
|
| 3 |
[
|
| 4 |
-
|
| 5 |
]
|
| 6 |
],
|
| 7 |
"bos_token_id": 0,
|
| 8 |
-
"decoder_start_token_id":
|
| 9 |
-
"eos_token_id":
|
| 10 |
-
"forced_eos_token_id":
|
| 11 |
"max_length": 512,
|
| 12 |
-
"num_beams":
|
| 13 |
-
"pad_token_id":
|
| 14 |
"renormalize_logits": true,
|
| 15 |
"transformers_version": "4.34.0.dev0"
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bad_words_ids": [
|
| 3 |
[
|
| 4 |
+
57829
|
| 5 |
]
|
| 6 |
],
|
| 7 |
"bos_token_id": 0,
|
| 8 |
+
"decoder_start_token_id": 57829,
|
| 9 |
+
"eos_token_id": 41756,
|
| 10 |
+
"forced_eos_token_id": 41756,
|
| 11 |
"max_length": 512,
|
| 12 |
+
"num_beams": 6,
|
| 13 |
+
"pad_token_id": 57829,
|
| 14 |
"renormalize_logits": true,
|
| 15 |
"transformers_version": "4.34.0.dev0"
|
| 16 |
}
|
model.safetensors
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 sha256:78b81c43b0752c41facfb4a7f2f007e3085f38289d3ddf0e37ac45b9c05ee19b
|
| 3 |
+
size 471295780
|
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 sha256:1ef6427a84c632b027ee9f892da540d30b23b60b94bc4b43e0c54a77e4108c0a
|
| 3 |
+
size 471352773
|