Upload T5ForConditionalGeneration
Browse files
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"T5ForConditionalGeneration"
|
| 4 |
],
|
|
@@ -6,11 +7,13 @@
|
|
| 6 |
"d_kv": 64,
|
| 7 |
"d_model": 4096,
|
| 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 |
"num_decoder_layers": 24,
|
|
@@ -22,7 +25,7 @@
|
|
| 22 |
"relative_attention_num_buckets": 32,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
"torch_dtype": "float32",
|
| 25 |
-
"transformers_version": "4.
|
| 26 |
"use_cache": true,
|
| 27 |
"vocab_size": 32128
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-xxl",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 7 |
"d_kv": 64,
|
| 8 |
"d_model": 4096,
|
| 9 |
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
"dropout_rate": 0.1,
|
| 12 |
"eos_token_id": 1,
|
| 13 |
"feed_forward_proj": "gated-gelu",
|
| 14 |
"initializer_factor": 1.0,
|
| 15 |
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": true,
|
| 17 |
"layer_norm_epsilon": 1e-06,
|
| 18 |
"model_type": "t5",
|
| 19 |
"num_decoder_layers": 24,
|
|
|
|
| 25 |
"relative_attention_num_buckets": 32,
|
| 26 |
"tie_word_embeddings": false,
|
| 27 |
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.30.2",
|
| 29 |
"use_cache": true,
|
| 30 |
"vocab_size": 32128
|
| 31 |
}
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 1,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 1,
|
| 5 |
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.30.2"
|
| 7 |
}
|
model-00001-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:220f643c5d341bfa6bcfe3485c90aaf7acba00e0d77348e35f97f7e16c23afcc
|
| 3 |
+
size 9989150328
|
model-00002-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c8b02f52841fbb7b64b48a7b07cf63392c2271b2e4804f53694f61c5c39d30b
|
| 3 |
+
size 9932577208
|
model-00003-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7eecf16b9b648fef6044259b4b49a7595b9ba2ba56aa403b92814ecc94a9b0ae
|
| 3 |
+
size 9999712664
|
model-00004-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9526c1dbc393ec001d2e34e7cfc524f44a2ca6e3197494dba443a09feb9bb75d
|
| 3 |
+
size 9999712416
|
model-00005-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13913b7329b9c5b1199903ee267ca8e2b7952099182774d219462a467d12203a
|
| 3 |
+
size 4620245888
|
model.safetensors.index.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|