Instructions to use kmfoda/long-t5-tglobal-xxl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kmfoda/long-t5-tglobal-xxl with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("kmfoda/long-t5-tglobal-xxl") model = AutoModelForSeq2SeqLM.from_pretrained("kmfoda/long-t5-tglobal-xxl", device_map="auto") - Notebooks
- Google Colab
- Kaggle
initial upload
Browse files
config.json
CHANGED
|
@@ -1,12 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"LongT5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
-
"d_ff":
|
| 7 |
"d_kv": 64,
|
| 8 |
"d_model": 1024,
|
| 9 |
"decoder_start_token_id": 0,
|
|
|
|
| 10 |
"dropout_rate": 0.1,
|
| 11 |
"encoder_attention_type": "transient-global",
|
| 12 |
"eos_token_id": 1,
|
|
@@ -14,20 +15,21 @@
|
|
| 14 |
"global_block_size": 16,
|
| 15 |
"initializer_factor": 1.0,
|
| 16 |
"is_encoder_decoder": true,
|
|
|
|
| 17 |
"layer_norm_epsilon": 1e-06,
|
| 18 |
"local_radius": 127,
|
| 19 |
"model_type": "longt5",
|
| 20 |
"n_positions": 4096,
|
| 21 |
"num_decoder_layers": 24,
|
| 22 |
-
"num_heads":
|
| 23 |
-
"num_layers":
|
| 24 |
"output_past": true,
|
| 25 |
"pad_token_id": 0,
|
| 26 |
"relative_attention_max_distance": 128,
|
| 27 |
"relative_attention_num_buckets": 32,
|
| 28 |
"tie_word_embeddings": false,
|
| 29 |
"torch_dtype": "float32",
|
| 30 |
-
"transformers_version": "4.
|
| 31 |
"use_cache": true,
|
| 32 |
"vocab_size": 32128
|
| 33 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "long-t5-tglobal-large",
|
| 3 |
"architectures": [
|
| 4 |
"LongT5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
+
"d_ff": 5120,
|
| 7 |
"d_kv": 64,
|
| 8 |
"d_model": 1024,
|
| 9 |
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
"dropout_rate": 0.1,
|
| 12 |
"encoder_attention_type": "transient-global",
|
| 13 |
"eos_token_id": 1,
|
|
|
|
| 15 |
"global_block_size": 16,
|
| 16 |
"initializer_factor": 1.0,
|
| 17 |
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
"layer_norm_epsilon": 1e-06,
|
| 20 |
"local_radius": 127,
|
| 21 |
"model_type": "longt5",
|
| 22 |
"n_positions": 4096,
|
| 23 |
"num_decoder_layers": 24,
|
| 24 |
+
"num_heads": 64,
|
| 25 |
+
"num_layers": 48,
|
| 26 |
"output_past": true,
|
| 27 |
"pad_token_id": 0,
|
| 28 |
"relative_attention_max_distance": 128,
|
| 29 |
"relative_attention_num_buckets": 32,
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.23.1",
|
| 33 |
"use_cache": true,
|
| 34 |
"vocab_size": 32128
|
| 35 |
}
|
pytorch_model.bin → pytorch_model-00001-of-00002.bin
RENAMED
|
@@ -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 sha256:1473694be8e475797e7d316847659cb3ef6ebb13041d854ea0d0b1b7eda2b297
|
| 3 |
+
size 9725042131
|
pytorch_model-00002-of-00002.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2fcf0e02cb4f6b5d41c1c1817f5b80dbb812870fd8721dcac4590cdd84ecfea
|
| 3 |
+
size 1511644089
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12ca3616ff8422a5cbf510b62876f29315db066e1256801b5931a70cabc3b620
|
| 3 |
+
size 79600
|