Upload T5ForConditionalGeneration
#28
by
Cactuss
- opened
- config.json +11 -6
- generation_config.json +1 -2
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -1,22 +1,26 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"T5ForConditionalGeneration"
|
| 4 |
],
|
| 5 |
-
"
|
|
|
|
| 6 |
"d_kv": 64,
|
| 7 |
-
"d_model":
|
| 8 |
"decoder_start_token_id": 0,
|
|
|
|
| 9 |
"dropout_rate": 0.1,
|
| 10 |
"eos_token_id": 1,
|
| 11 |
"feed_forward_proj": "gated-gelu",
|
| 12 |
"initializer_factor": 1.0,
|
| 13 |
"is_encoder_decoder": true,
|
|
|
|
| 14 |
"layer_norm_epsilon": 1e-06,
|
| 15 |
"model_type": "t5",
|
| 16 |
"n_positions": 512,
|
| 17 |
-
"num_decoder_layers":
|
| 18 |
-
"num_heads":
|
| 19 |
-
"num_layers":
|
| 20 |
"output_past": true,
|
| 21 |
"pad_token_id": 0,
|
| 22 |
"relative_attention_max_distance": 128,
|
|
@@ -51,7 +55,8 @@
|
|
| 51 |
}
|
| 52 |
},
|
| 53 |
"tie_word_embeddings": false,
|
| 54 |
-
"
|
|
|
|
| 55 |
"use_cache": true,
|
| 56 |
"vocab_size": 32128
|
| 57 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-small",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 1024,
|
| 8 |
"d_kv": 64,
|
| 9 |
+
"d_model": 512,
|
| 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,
|
| 21 |
+
"num_decoder_layers": 8,
|
| 22 |
+
"num_heads": 6,
|
| 23 |
+
"num_layers": 8,
|
| 24 |
"output_past": true,
|
| 25 |
"pad_token_id": 0,
|
| 26 |
"relative_attention_max_distance": 128,
|
|
|
|
| 55 |
}
|
| 56 |
},
|
| 57 |
"tie_word_embeddings": false,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.35.2",
|
| 60 |
"use_cache": true,
|
| 61 |
"vocab_size": 32128
|
| 62 |
}
|
generation_config.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 1,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"decoder_start_token_id": 0,
|
| 3 |
"eos_token_id": 1,
|
| 4 |
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.35.2"
|
| 6 |
}
|
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:e7fb40c6be901a7d46b384898cd502fbb198c98dec2a827ced9406db4919ab0f
|
| 3 |
+
size 307867048
|