Instructions to use Splend1dchan/byt5-base-squad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Splend1dchan/byt5-base-squad with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Splend1dchan/byt5-base-squad") model = AutoModelForSeq2SeqLM.from_pretrained("Splend1dchan/byt5-base-squad") - Notebooks
- Google Colab
- Kaggle
Commit ·
3600ae1
1
Parent(s): 9609c53
1epochs
Browse files- .gitignore +1 -0
- config.json +30 -0
- pytorch_model.bin +3 -0
- runs/Apr10_00-02-42_stwl6pctr1649515016669-j28st/1649520191.6872473/events.out.tfevents.1649520191.stwl6pctr1649515016669-j28st.1485.5 +3 -0
- runs/Apr10_00-02-42_stwl6pctr1649515016669-j28st/events.out.tfevents.1649520191.stwl6pctr1649515016669-j28st.1485.4 +3 -0
- runs/Apr10_00-10-06_stwl6pctr1649515016669-j28st/1649520639.5143168/events.out.tfevents.1649520639.stwl6pctr1649515016669-j28st.2458.1 +3 -0
- runs/Apr10_00-10-06_stwl6pctr1649515016669-j28st/events.out.tfevents.1649520639.stwl6pctr1649515016669-j28st.2458.0 +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/byt5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"d_ff": 3968,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 1536,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dropout_rate": 0.1,
|
| 11 |
+
"eos_token_id": 1,
|
| 12 |
+
"feed_forward_proj": "gated-gelu",
|
| 13 |
+
"gradient_checkpointing": false,
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"layer_norm_epsilon": 1e-06,
|
| 17 |
+
"model_type": "t5",
|
| 18 |
+
"num_decoder_layers": 6,
|
| 19 |
+
"num_heads": 12,
|
| 20 |
+
"num_layers": 18,
|
| 21 |
+
"output_past": true,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"relative_attention_num_buckets": 32,
|
| 24 |
+
"tie_word_embeddings": false,
|
| 25 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 26 |
+
"torch_dtype": "float32",
|
| 27 |
+
"transformers_version": "4.17.0",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 384
|
| 30 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b649cb7fb070d1c7590dca2bdbed7f73239f114e3f43d4cea482648b3504d72
|
| 3 |
+
size 721420288
|
runs/Apr10_00-02-42_stwl6pctr1649515016669-j28st/1649520191.6872473/events.out.tfevents.1649520191.stwl6pctr1649515016669-j28st.1485.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11fd04176b0db682826e69f8c673c70283dcd967108b26f5b59de0abf51fd527
|
| 3 |
+
size 4770
|
runs/Apr10_00-02-42_stwl6pctr1649515016669-j28st/events.out.tfevents.1649520191.stwl6pctr1649515016669-j28st.1485.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3387891a0ad7af4483b492ce99d5f645478c9bd9393748b4b4ba5d4df96a3c9e
|
| 3 |
+
size 3366
|
runs/Apr10_00-10-06_stwl6pctr1649515016669-j28st/1649520639.5143168/events.out.tfevents.1649520639.stwl6pctr1649515016669-j28st.2458.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5bd9a555a9617975acad01565e376cccde2cc484afbc4c7894518794b64d50a
|
| 3 |
+
size 4770
|
runs/Apr10_00-10-06_stwl6pctr1649515016669-j28st/events.out.tfevents.1649520639.stwl6pctr1649515016669-j28st.2458.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8744f7ab883c16269652f86f61b90f7ce936fe8dd2847957609e1d9ddfad5bca
|
| 3 |
+
size 3525
|