Upload TFLongT5ForConditionalGeneration
Browse files- README.md +48 -0
- config.json +35 -0
- tf_model.h5 +3 -0
README.md
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_keras_callback
|
| 5 |
+
model-index:
|
| 6 |
+
- name: long-t5-tglobal-large
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information Keras had access to. You should
|
| 11 |
+
probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# long-t5-tglobal-large
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [google/long-t5-tglobal-large](https://huggingface.co/google/long-t5-tglobal-large) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- optimizer: None
|
| 37 |
+
- training_precision: float32
|
| 38 |
+
|
| 39 |
+
### Training results
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
### Framework versions
|
| 44 |
+
|
| 45 |
+
- Transformers 4.24.0.dev0
|
| 46 |
+
- TensorFlow 2.9.0
|
| 47 |
+
- Datasets 2.2.2
|
| 48 |
+
- Tokenizers 0.11.6
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/long-t5-tglobal-large",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LongT5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 2816,
|
| 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,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 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": 16,
|
| 25 |
+
"num_layers": 24,
|
| 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": "4.24.0.dev0",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 32128
|
| 35 |
+
}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e45d204e21e4fa51ce09a0a4eea970c3be5fe88fb41fbb5a8fde1e599dd3ed1
|
| 3 |
+
size 3397054624
|