jeydipak valeriedaash commited on
Commit
a493f60
β€’
1 Parent(s): 4235e44

Update README.md (#1)

Browse files

- Update README.md (6dd10c6ade940960072362ef00b5b5c2a6badb3a)


Co-authored-by: Valeriia Dashieva <valeriedaash@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +19 -1
README.md CHANGED
@@ -9,5 +9,23 @@ app_file: app.py
9
  pinned: false
10
  license: apache-2.0
11
  ---
 
 
 
 
 
 
 
 
 
12
 
13
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
9
  pinned: false
10
  license: apache-2.0
11
  ---
12
+ # Streamlit app for NLP tasks πŸ’‘
13
+ 1. Film review classification on 'Good', 'Bad', 'Neutral' classes
14
+ 2. Assessing the toxicity of a user message
15
+ 3. Text generation using the GPT model using a custom prompt
16
+
17
+ ## Team πŸ§‘πŸ»β€πŸ’»
18
+ 1. [Alexey Kamaev](https://github.com/AlexeyKamaev)
19
+ 2. [Marina Kochetova](https://github.com/neonanet)
20
+ 3. [Valeriia Dashieva](https://github.com/valeriedaash)
21
 
22
+ ## Used models πŸ€–
23
+ 1. For classification task we trained 3 models: TF-IDF vectorizer + LogReg, Word2Vec + LogReg, RuBert + LogReg
24
+ 2. For toxicity assessing task we trained rubert-tiny-toxicity
25
+ 3. For Text generation task we trained rugpt3small_based_on_gpt2
26
+
27
+ ## Used instruments 🧰
28
+ 1. Python.
29
+ 2. Pytorch.
30
+ 3. Transformers
31
+ 4. [Streamlit](https://nnproject1-6tcyg5tnwo2we6fg8gqbgt.streamlit.app).