Upload T5ForConditionalGeneration
Browse files- config.json +5 -4
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -4,17 +4,17 @@
|
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
"classifier_dropout": 0.0,
|
| 7 |
-
"d_ff":
|
| 8 |
"d_kv": 64,
|
| 9 |
"d_model": 768,
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
-
"dense_act_fn": "
|
| 12 |
"dropout_rate": 0.1,
|
| 13 |
"eos_token_id": 1,
|
| 14 |
-
"feed_forward_proj": "
|
| 15 |
"initializer_factor": 1.0,
|
| 16 |
"is_encoder_decoder": true,
|
| 17 |
-
"is_gated_act":
|
| 18 |
"layer_norm_epsilon": 1e-06,
|
| 19 |
"model_type": "t5",
|
| 20 |
"n_positions": 512,
|
|
@@ -54,6 +54,7 @@
|
|
| 54 |
"prefix": "translate English to Romanian: "
|
| 55 |
}
|
| 56 |
},
|
|
|
|
| 57 |
"torch_dtype": "float32",
|
| 58 |
"transformers_version": "4.42.3",
|
| 59 |
"use_cache": true,
|
|
|
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2048,
|
| 8 |
"d_kv": 64,
|
| 9 |
"d_model": 768,
|
| 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 |
"initializer_factor": 1.0,
|
| 16 |
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
"layer_norm_epsilon": 1e-06,
|
| 19 |
"model_type": "t5",
|
| 20 |
"n_positions": 512,
|
|
|
|
| 54 |
"prefix": "translate English to Romanian: "
|
| 55 |
}
|
| 56 |
},
|
| 57 |
+
"tie_word_embeddings": false,
|
| 58 |
"torch_dtype": "float32",
|
| 59 |
"transformers_version": "4.42.3",
|
| 60 |
"use_cache": true,
|
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 sha256:48b2ce5850d1791facb017e2d3be9606ab8d50693f6203c1d8dba1a4e6287d66
|
| 3 |
+
size 990191464
|