remove final_logits_bias
Browse files- config.json +4 -0
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"activation_dropout": 0.0,
|
| 3 |
"activation_function": "relu",
|
| 4 |
"architectures": [
|
|
@@ -13,6 +14,7 @@
|
|
| 13 |
"decoder_layers": 24,
|
| 14 |
"decoder_start_token_id": 2,
|
| 15 |
"dropout": 0.1,
|
|
|
|
| 16 |
"encoder_attention_heads": 16,
|
| 17 |
"encoder_ffn_dim": 8192,
|
| 18 |
"encoder_layerdrop": 0.05,
|
|
@@ -21,8 +23,10 @@
|
|
| 21 |
"gradient_checkpointing": false,
|
| 22 |
"init_std": 0.02,
|
| 23 |
"is_encoder_decoder": true,
|
|
|
|
| 24 |
"max_position_embeddings": 1024,
|
| 25 |
"model_type": "m2m_100",
|
|
|
|
| 26 |
"num_hidden_layers": 24,
|
| 27 |
"pad_token_id": 1,
|
| 28 |
"scale_embedding": true,
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "hf_models/m2m100_1.2B/",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "relu",
|
| 5 |
"architectures": [
|
| 14 |
"decoder_layers": 24,
|
| 15 |
"decoder_start_token_id": 2,
|
| 16 |
"dropout": 0.1,
|
| 17 |
+
"early_stopping": true,
|
| 18 |
"encoder_attention_heads": 16,
|
| 19 |
"encoder_ffn_dim": 8192,
|
| 20 |
"encoder_layerdrop": 0.05,
|
| 23 |
"gradient_checkpointing": false,
|
| 24 |
"init_std": 0.02,
|
| 25 |
"is_encoder_decoder": true,
|
| 26 |
+
"max_length": 200,
|
| 27 |
"max_position_embeddings": 1024,
|
| 28 |
"model_type": "m2m_100",
|
| 29 |
+
"num_beams": 5,
|
| 30 |
"num_hidden_layers": 24,
|
| 31 |
"pad_token_id": 1,
|
| 32 |
"scale_embedding": true,
|
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:a58ef8f42362ef12adeddc600b3425f1e2bbd019cfa6aae6b0051e2e3e055cd4
|
| 3 |
+
size 4958230644
|