Commit
·
e46e3a3
1
Parent(s):
d0504f5
XXL model bf16
Browse files- config.json +4 -34
- pytorch_model-00001-of-00002.bin +2 -2
- pytorch_model-00002-of-00002.bin +2 -2
- pytorch_model.bin.index.json +1 -1
config.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "google/
|
| 3 |
"architectures": [
|
| 4 |
"T5EncoderModel"
|
| 5 |
],
|
| 6 |
-
"d_ff":
|
| 7 |
"d_kv": 64,
|
| 8 |
-
"d_model":
|
| 9 |
"decoder_start_token_id": 0,
|
| 10 |
"dense_act_fn": "gelu_new",
|
| 11 |
"dropout_rate": 0.1,
|
|
@@ -16,43 +16,13 @@
|
|
| 16 |
"is_gated_act": true,
|
| 17 |
"layer_norm_epsilon": 1e-06,
|
| 18 |
"model_type": "t5",
|
| 19 |
-
"n_positions": 512,
|
| 20 |
"num_decoder_layers": 24,
|
| 21 |
-
"num_heads":
|
| 22 |
"num_layers": 24,
|
| 23 |
"output_past": true,
|
| 24 |
"pad_token_id": 0,
|
| 25 |
"relative_attention_max_distance": 128,
|
| 26 |
"relative_attention_num_buckets": 32,
|
| 27 |
-
"task_specific_params": {
|
| 28 |
-
"summarization": {
|
| 29 |
-
"early_stopping": true,
|
| 30 |
-
"length_penalty": 2.0,
|
| 31 |
-
"max_length": 200,
|
| 32 |
-
"min_length": 30,
|
| 33 |
-
"no_repeat_ngram_size": 3,
|
| 34 |
-
"num_beams": 4,
|
| 35 |
-
"prefix": "summarize: "
|
| 36 |
-
},
|
| 37 |
-
"translation_en_to_de": {
|
| 38 |
-
"early_stopping": true,
|
| 39 |
-
"max_length": 300,
|
| 40 |
-
"num_beams": 4,
|
| 41 |
-
"prefix": "translate English to German: "
|
| 42 |
-
},
|
| 43 |
-
"translation_en_to_fr": {
|
| 44 |
-
"early_stopping": true,
|
| 45 |
-
"max_length": 300,
|
| 46 |
-
"num_beams": 4,
|
| 47 |
-
"prefix": "translate English to French: "
|
| 48 |
-
},
|
| 49 |
-
"translation_en_to_ro": {
|
| 50 |
-
"early_stopping": true,
|
| 51 |
-
"max_length": 300,
|
| 52 |
-
"num_beams": 4,
|
| 53 |
-
"prefix": "translate English to Romanian: "
|
| 54 |
-
}
|
| 55 |
-
},
|
| 56 |
"tie_word_embeddings": false,
|
| 57 |
"torch_dtype": "bfloat16",
|
| 58 |
"transformers_version": "4.23.1",
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "google/t5-v1_1-xxl",
|
| 3 |
"architectures": [
|
| 4 |
"T5EncoderModel"
|
| 5 |
],
|
| 6 |
+
"d_ff": 10240,
|
| 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,
|
|
|
|
| 16 |
"is_gated_act": true,
|
| 17 |
"layer_norm_epsilon": 1e-06,
|
| 18 |
"model_type": "t5",
|
|
|
|
| 19 |
"num_decoder_layers": 24,
|
| 20 |
+
"num_heads": 64,
|
| 21 |
"num_layers": 24,
|
| 22 |
"output_past": true,
|
| 23 |
"pad_token_id": 0,
|
| 24 |
"relative_attention_max_distance": 128,
|
| 25 |
"relative_attention_num_buckets": 32,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"tie_word_embeddings": false,
|
| 27 |
"torch_dtype": "bfloat16",
|
| 28 |
"transformers_version": "4.23.1",
|
pytorch_model-00001-of-00002.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 sha256:15155416b2bbeaf9d9c8a787c7afbc5f9b941d3cad6f5bdf34196e3d7b3aedbc
|
| 3 |
+
size 4726161628
|
pytorch_model-00002-of-00002.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 sha256:04bb62ab955f41131fbb8450699bf01298220860c81185fb0f20eeeccd9daeac
|
| 3 |
+
size 4798535559
|
pytorch_model.bin.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 9787813888
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
|