Upload 9 files
Browse files- Multi_class_text_classifica_fine_tuning_distilbert (1).ipynb +0 -0
- app.py +26 -0
- distilbert_fine_tuned_model.zip +3 -0
- distilbert_fine_tuned_model/config.json +39 -0
- distilbert_fine_tuned_model/model.safetensors +3 -0
- distilbert_fine_tuned_model/special_tokens_map.json +7 -0
- distilbert_fine_tuned_model/tokenizer_config.json +58 -0
- distilbert_fine_tuned_model/vocab.txt +0 -0
- requirements.txt +4 -0
Multi_class_text_classifica_fine_tuning_distilbert (1).ipynb
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
app.py
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
|
| 3 |
+
import torch
|
| 4 |
+
|
| 5 |
+
st.title("Multi classification Fine tunning model")
|
| 6 |
+
|
| 7 |
+
# Load model and tokenizer
|
| 8 |
+
model_dir = "distilbert_fine_tuned_model"
|
| 9 |
+
tokenizer = DistilBertTokenizer.from_pretrained(model_dir)
|
| 10 |
+
model = DistilBertForSequenceClassification.from_pretrained(model_dir)
|
| 11 |
+
|
| 12 |
+
def predict_class(text):
|
| 13 |
+
inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
|
| 14 |
+
|
| 15 |
+
outputs = model(**inputs)
|
| 16 |
+
|
| 17 |
+
prediction_value = torch.argmax(outputs.logits, dim=1).item()
|
| 18 |
+
|
| 19 |
+
stars=[" 1 stars"," 2 stars"," 3 stars"," 4 stars"," 5 stars"]
|
| 20 |
+
st.write(stars[prediction_value])
|
| 21 |
+
|
| 22 |
+
inputs_text=st.text_input("Please enter the text",value="I think I really like this place. Ayesha and I had a chance to visit Cheuvront on a Monday night. It wasn\'t terribly busy when we arrived and we were warmly greeted. Unfortunately we were seated next to a loud group of young children that thought they knew something of the world ")
|
| 23 |
+
|
| 24 |
+
if st.button("submit"):
|
| 25 |
+
predict_class(inputs_text)
|
| 26 |
+
|
distilbert_fine_tuned_model.zip
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00dcb1272610a3d359eb3bd2cee0e378a3dc6b15f01916e77edcc1ab79c94760
|
| 3 |
+
size 247110488
|
distilbert_fine_tuned_model/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"LABEL_0": 0,
|
| 21 |
+
"LABEL_1": 1,
|
| 22 |
+
"LABEL_2": 2,
|
| 23 |
+
"LABEL_3": 3,
|
| 24 |
+
"LABEL_4": 4
|
| 25 |
+
},
|
| 26 |
+
"max_position_embeddings": 512,
|
| 27 |
+
"model_type": "distilbert",
|
| 28 |
+
"n_heads": 12,
|
| 29 |
+
"n_layers": 6,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"qa_dropout": 0.1,
|
| 33 |
+
"seq_classif_dropout": 0.2,
|
| 34 |
+
"sinusoidal_pos_embds": false,
|
| 35 |
+
"tie_weights_": true,
|
| 36 |
+
"torch_dtype": "float32",
|
| 37 |
+
"transformers_version": "4.48.3",
|
| 38 |
+
"vocab_size": 30522
|
| 39 |
+
}
|
distilbert_fine_tuned_model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d9d4ae88594153c7e78a37d3c34087496743b95ca96df986b35a44b032c871a
|
| 3 |
+
size 267841796
|
distilbert_fine_tuned_model/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
distilbert_fine_tuned_model/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
distilbert_fine_tuned_model/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
requirements.txt
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
transformers
|
| 2 |
+
pandas==2.2.2
|
| 3 |
+
torch==2.5.1
|
| 4 |
+
transformers==4.48.3
|