Instructions to use summervent/speller-example_ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use summervent/speller-example_ with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("summervent/speller-example_") model = AutoModelForSeq2SeqLM.from_pretrained("summervent/speller-example_", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
7e06b7e
1
Parent(s): 62177d7
Training in progress, step 5000
Browse files- .gitignore +1 -0
- config.json +62 -0
- pytorch_model.bin +3 -0
- runs/Feb09_18-15-55_3b4ae47df1bd/1675966562.683126/events.out.tfevents.1675966562.3b4ae47df1bd.24713.1 +3 -0
- runs/Feb09_18-15-55_3b4ae47df1bd/events.out.tfevents.1675966562.3b4ae47df1bd.24713.0 +3 -0
- tokenizer.json +16 -2
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "sberbank-ai/ruT5-base",
|
| 3 |
+
"_num_labels": 2,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"T5ForConditionalGeneration"
|
| 6 |
+
],
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"max_length": 256,
|
| 20 |
+
"model_type": "t5",
|
| 21 |
+
"n_positions": 512,
|
| 22 |
+
"num_decoder_layers": 12,
|
| 23 |
+
"num_heads": 12,
|
| 24 |
+
"num_layers": 12,
|
| 25 |
+
"output_past": true,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"relative_attention_max_distance": 128,
|
| 28 |
+
"relative_attention_num_buckets": 32,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"summarization": {
|
| 31 |
+
"early_stopping": true,
|
| 32 |
+
"length_penalty": 2.0,
|
| 33 |
+
"max_length": 200,
|
| 34 |
+
"min_length": 30,
|
| 35 |
+
"no_repeat_ngram_size": 3,
|
| 36 |
+
"num_beams": 4,
|
| 37 |
+
"prefix": "summarize: "
|
| 38 |
+
},
|
| 39 |
+
"translation_en_to_de": {
|
| 40 |
+
"early_stopping": true,
|
| 41 |
+
"max_length": 300,
|
| 42 |
+
"num_beams": 4,
|
| 43 |
+
"prefix": "translate English to German: "
|
| 44 |
+
},
|
| 45 |
+
"translation_en_to_fr": {
|
| 46 |
+
"early_stopping": true,
|
| 47 |
+
"max_length": 300,
|
| 48 |
+
"num_beams": 4,
|
| 49 |
+
"prefix": "translate English to French: "
|
| 50 |
+
},
|
| 51 |
+
"translation_en_to_ro": {
|
| 52 |
+
"early_stopping": true,
|
| 53 |
+
"max_length": 300,
|
| 54 |
+
"num_beams": 4,
|
| 55 |
+
"prefix": "translate English to Romanian: "
|
| 56 |
+
}
|
| 57 |
+
},
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.26.0",
|
| 60 |
+
"use_cache": true,
|
| 61 |
+
"vocab_size": 32128
|
| 62 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:503d6230c99d75038894fdaf986a3fc965ea70759f9c785970870991486267e3
|
| 3 |
+
size 891702929
|
runs/Feb09_18-15-55_3b4ae47df1bd/1675966562.683126/events.out.tfevents.1675966562.3b4ae47df1bd.24713.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb96eb869405972e15f44edfcfec24bbbf1c92afc7b060326d321a2e3638a31a
|
| 3 |
+
size 5903
|
runs/Feb09_18-15-55_3b4ae47df1bd/events.out.tfevents.1675966562.3b4ae47df1bd.24713.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fe743c4b2ccaa7c7e355a52b0abdfdf2283cb6177f601226b1135f4392ea419
|
| 3 |
+
size 84832
|
tokenizer.json
CHANGED
|
@@ -1,7 +1,21 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 256,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 256
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 0,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "<pad>"
|
| 18 |
+
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93cfca22ef4e2f4bbada5a629acc499e329758a93658f3504012704625694751
|
| 3 |
+
size 3579
|