nicholasKluge commited on
Commit
8b3ddab
1 Parent(s): fd8c72c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -8
README.md CHANGED
@@ -16,11 +16,11 @@ widget:
16
  - text: "Esqueceram de mim 2 é o pior filme da franquia inteira."
17
  example_title: Exemplo
18
  ---
19
- # TeenyTinyLlama-162m-IMDB
20
 
21
  TeenyTinyLlama is a series of small foundational models trained in Brazilian Portuguese.
22
 
23
- This repository contains a version of [TeenyTinyLlama-162m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-162m) (`TeenyTinyLlama-162m-IMDB`) fine-tuned on the the [IMDB dataset](https://huggingface.co/datasets/christykoh/imdb_pt).
24
 
25
  ## Details
26
 
@@ -38,7 +38,7 @@ from transformers import pipeline
38
 
39
  text = "Esqueceram de mim 2 é um dos melhores filmes de natal de todos os tempos."
40
 
41
- classifier = pipeline("text-classification", model="nicholasKluge/TeenyTinyLlama-162m-IMDB")
42
  classifier(text)
43
 
44
  # >>> [{'label': 'POSITIVE', 'score': 0.9971244931221008}]
@@ -63,13 +63,13 @@ dataset = load_dataset("christykoh/imdb_pt")
63
 
64
  # Create a `ModelForSequenceClassification`
65
  model = AutoModelForSequenceClassification.from_pretrained(
66
- "nicholasKluge/TeenyTinyLlama-162m",
67
  num_labels=2,
68
  id2label={0: "NEGATIVE", 1: "POSITIVE"},
69
  label2id={"NEGATIVE": 0, "POSITIVE": 1}
70
  )
71
 
72
- tokenizer = AutoTokenizer.from_pretrained("nicholasKluge/TeenyTinyLlama-162m")
73
 
74
  # Preprocess the dataset
75
  def preprocess_function(examples):
@@ -124,7 +124,7 @@ trainer.train()
124
 
125
  | Models | [IMDB](https://huggingface.co/datasets/christykoh/imdb_pt) |
126
  |--------------------------------------------------------------------------------------------|------------------------------------------------------------|
127
- | [Teeny Tiny Llama 162m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-162m) | 91.14 |
128
  | [Bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) | 92.22 |
129
  | [Bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased)| 93.58 |
130
  | [Gpt2-small-portuguese](https://huggingface.co/pierreguillou/gpt2-small-portuguese) | 91.60 |
@@ -135,7 +135,7 @@ trainer.train()
135
 
136
  @misc{nicholas22llama,
137
  doi = {10.5281/zenodo.6989727},
138
- url = {https://huggingface.co/nicholasKluge/TeenyTinyLlama-162m},
139
  author = {Nicholas Kluge Corrêa},
140
  title = {TeenyTinyLlama},
141
  year = {2023},
@@ -151,4 +151,4 @@ This repository was built as part of the RAIES ([Rede de Inteligência Artificia
151
 
152
  ## License
153
 
154
- TeenyTinyLlama-162m-IMDB is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
 
16
  - text: "Esqueceram de mim 2 é o pior filme da franquia inteira."
17
  example_title: Exemplo
18
  ---
19
+ # TeenyTinyLlama-160m-IMDB
20
 
21
  TeenyTinyLlama is a series of small foundational models trained in Brazilian Portuguese.
22
 
23
+ This repository contains a version of [TeenyTinyLlama-160m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-160m) (`TeenyTinyLlama-160m-IMDB`) fine-tuned on the the [IMDB dataset](https://huggingface.co/datasets/christykoh/imdb_pt).
24
 
25
  ## Details
26
 
 
38
 
39
  text = "Esqueceram de mim 2 é um dos melhores filmes de natal de todos os tempos."
40
 
41
+ classifier = pipeline("text-classification", model="nicholasKluge/TeenyTinyLlama-160m-IMDB")
42
  classifier(text)
43
 
44
  # >>> [{'label': 'POSITIVE', 'score': 0.9971244931221008}]
 
63
 
64
  # Create a `ModelForSequenceClassification`
65
  model = AutoModelForSequenceClassification.from_pretrained(
66
+ "nicholasKluge/TeenyTinyLlama-160m",
67
  num_labels=2,
68
  id2label={0: "NEGATIVE", 1: "POSITIVE"},
69
  label2id={"NEGATIVE": 0, "POSITIVE": 1}
70
  )
71
 
72
+ tokenizer = AutoTokenizer.from_pretrained("nicholasKluge/TeenyTinyLlama-160m")
73
 
74
  # Preprocess the dataset
75
  def preprocess_function(examples):
 
124
 
125
  | Models | [IMDB](https://huggingface.co/datasets/christykoh/imdb_pt) |
126
  |--------------------------------------------------------------------------------------------|------------------------------------------------------------|
127
+ | [Teeny Tiny Llama 160m](https://huggingface.co/nicholasKluge/TeenyTinyLlama-160m) | 91.14 |
128
  | [Bert-base-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased) | 92.22 |
129
  | [Bert-large-portuguese-cased](https://huggingface.co/neuralmind/bert-base-portuguese-cased)| 93.58 |
130
  | [Gpt2-small-portuguese](https://huggingface.co/pierreguillou/gpt2-small-portuguese) | 91.60 |
 
135
 
136
  @misc{nicholas22llama,
137
  doi = {10.5281/zenodo.6989727},
138
+ url = {https://huggingface.co/nicholasKluge/TeenyTinyLlama-160m},
139
  author = {Nicholas Kluge Corrêa},
140
  title = {TeenyTinyLlama},
141
  year = {2023},
 
151
 
152
  ## License
153
 
154
+ TeenyTinyLlama-160m-IMDB is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.