Spaces:
Sleeping
Sleeping
added wraper for all models changed formatting and spelling mistakes.
Browse files
app.py
CHANGED
@@ -12,17 +12,52 @@ import pandas as pd
|
|
12 |
def parse_pipe_sa(pipe_out_text: str):
|
13 |
output_list = list(pipe_out_text)
|
14 |
pipe_label = output_list[0]['label']
|
15 |
-
pipe_score = output_list[0]['score']
|
16 |
|
17 |
parsed_prediction = 'NULL'
|
18 |
|
19 |
if pipe_label == 'NEGATIVE' or pipe_label == 'LABEL_0':
|
20 |
-
parsed_prediction = f'This model thinks the sentiment is
|
21 |
elif pipe_label == 'POSITIVE' or pipe_label == 'LABEL_1':
|
22 |
-
parsed_prediction = f'This model thinks the sentiment is
|
23 |
|
24 |
return parsed_prediction
|
25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
loraModel = AutoPeftModelForSequenceClassification.from_pretrained("Intradiction/text_classification_WithLORA")
|
27 |
#tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
|
28 |
tokenizer1 = AutoTokenizer.from_pretrained("albert-base-v2")
|
@@ -64,13 +99,13 @@ AlbertwithLORA_pipe = pipeline("text-classification",model=sa_merged_model1, tok
|
|
64 |
|
65 |
#NLI models
|
66 |
def AlbertnoLORA_fn(text1, text2):
|
67 |
-
return AlbertnoLORA_pipe({'text': text1, 'text_pair': text2})
|
68 |
|
69 |
def AlbertwithLORA_fn(text1, text2):
|
70 |
-
return AlbertwithLORA_pipe({'text': text1, 'text_pair': text2})
|
71 |
|
72 |
def AlbertUntrained_fn(text1, text2):
|
73 |
-
return ALbertUntrained_pipe({'text': text1, 'text_pair': text2})
|
74 |
|
75 |
|
76 |
# Handle calls to Deberta--------------------------------------------
|
@@ -86,14 +121,14 @@ DebertawithLORA_pipe = pipeline("text-classification",model=sa_merged_model2, to
|
|
86 |
|
87 |
#STS models
|
88 |
def DebertanoLORA_fn(text1, text2):
|
89 |
-
return DebertanoLORA_pipe({'text': text1, 'text_pair': text2})
|
90 |
|
91 |
def DebertawithLORA_fn(text1, text2):
|
92 |
-
return DebertawithLORA_pipe({'text': text1, 'text_pair': text2})
|
93 |
#return ("working2")
|
94 |
|
95 |
def DebertaUntrained_fn(text1, text2):
|
96 |
-
return DebertaUntrained_pipe({'text': text1, 'text_pair': text2})
|
97 |
|
98 |
#helper functions ------------------------------------------------------
|
99 |
|
@@ -321,10 +356,11 @@ with gr.Blocks(
|
|
321 |
with gr.Column(variant="panel"):
|
322 |
gr.Markdown("""
|
323 |
<h2>Specifications</h2>
|
324 |
-
<p><b>Model:</b>
|
|
|
325 |
<b>Dataset:</b> IMDB Movie review dataset <br>
|
326 |
<b>NLP Task:</b> Text Classification</p>
|
327 |
-
<p>Text classification is an NLP task that focuses on automatically ascribing a predefined category or labels to an input prompt. In this demonstration the Tiny Bert model has been used to classify the text on the basis of sentiment analysis, where the labels (negative and positive) will indicate the emotional state expressed by the input prompt
|
328 |
""")
|
329 |
|
330 |
with gr.Column(variant="panel"):
|
@@ -371,9 +407,10 @@ with gr.Blocks(
|
|
371 |
gr.Markdown("""
|
372 |
<h2>Specifications</h2>
|
373 |
<p><b>Model:</b> Albert <br>
|
|
|
374 |
<b>Dataset:</b> Stanford Natural Language Inference Dataset <br>
|
375 |
-
<b>NLP Task:</b>
|
376 |
-
<p>Natural Language Inference (NLI) which can also be referred to as Textual Entailment is an NLP task with the objective of determining the relationship between two pieces of text.
|
377 |
""")
|
378 |
with gr.Column(variant="panel"):
|
379 |
nli_p1 = gr.Textbox(placeholder="Prompt One",label= "Enter Query")
|
@@ -381,21 +418,21 @@ with gr.Blocks(
|
|
381 |
nli_btn = gr.Button("Run")
|
382 |
btnNLIStats = gr.Button("Display Training Metrics")
|
383 |
btnTensorLinkNLICon = gr.Button(value="View Conventional Training Graphs", link="https://huggingface.co/m4faisal/NLI-Conventional-Fine-Tuning/tensorboard")
|
384 |
-
btnTensorLinkNLILora = gr.Button(value="View LoRA Training Graphs", link="https://huggingface.co/m4faisal/NLI-Lora-Fine-Tuning-10K/tensorboard")
|
385 |
gr.Examples(
|
386 |
[
|
387 |
-
"
|
388 |
"People like apples",
|
389 |
-
"
|
390 |
],
|
391 |
nli_p1,
|
392 |
label="Try asking",
|
393 |
)
|
394 |
gr.Examples(
|
395 |
[
|
396 |
-
"
|
397 |
"Apples are good",
|
398 |
-
"
|
399 |
],
|
400 |
nli_p2,
|
401 |
label="Try asking",
|
@@ -430,9 +467,10 @@ with gr.Blocks(
|
|
430 |
gr.Markdown("""
|
431 |
<h2>Specifications</h2>
|
432 |
<p><b>Model:</b> Roberta Base <br>
|
|
|
433 |
<b>Dataset:</b> Semantic Text Similarity Benchmark <br>
|
434 |
<b>NLP Task:</b> Semantic Text Similarity</p>
|
435 |
-
<p>Semantic text similarity measures the closeness in meaning of two pieces of text despite differences in their wording or structure. This task involves two input prompts which can be sentences, phrases or entire documents and assessing them for similarity.
|
436 |
""")
|
437 |
with gr.Column(variant="panel"):
|
438 |
sts_p1 = gr.Textbox(placeholder="Prompt One",label= "Enter Query")
|
|
|
12 |
def parse_pipe_sa(pipe_out_text: str):
|
13 |
output_list = list(pipe_out_text)
|
14 |
pipe_label = output_list[0]['label']
|
15 |
+
pipe_score = float(output_list[0]['score'])*100
|
16 |
|
17 |
parsed_prediction = 'NULL'
|
18 |
|
19 |
if pipe_label == 'NEGATIVE' or pipe_label == 'LABEL_0':
|
20 |
+
parsed_prediction = f'This model thinks the sentiment is NEGATIVE. \nConfidence score of {pipe_score:.3f}%'
|
21 |
elif pipe_label == 'POSITIVE' or pipe_label == 'LABEL_1':
|
22 |
+
parsed_prediction = f'This model thinks the sentiment is POSITIVE. \nConfidence score of {pipe_score:.3f}%'
|
23 |
|
24 |
return parsed_prediction
|
25 |
|
26 |
+
# Parse sentiment NLI pipeline results
|
27 |
+
def parse_pipe_nli(pipe_out_text: str):
|
28 |
+
output_list = pipe_out_text
|
29 |
+
pipe_label = output_list['label']
|
30 |
+
pipe_score = float(output_list['score'])*100
|
31 |
+
|
32 |
+
parsed_prediction = 'NULL'
|
33 |
+
|
34 |
+
if pipe_label == 'NEGATIVE' or pipe_label == 'LABEL_0':
|
35 |
+
parsed_prediction = f'This model thinks the clauses CONFIRM each other. \nConfidence score of {pipe_score:.3f}'
|
36 |
+
elif pipe_label == 'POSITIVE' or pipe_label == 'LABEL_1':
|
37 |
+
parsed_prediction = f'This model thinks the clauses are Neutral. \nConfidence score of {pipe_score:.3f}'
|
38 |
+
elif pipe_label == 'POSITIVE' or pipe_label == 'LABEL_2':
|
39 |
+
parsed_prediction = f'This model thinks the clauses CONTRADICT each other. \nConfidence score of {pipe_score:.3f}'
|
40 |
+
|
41 |
+
return parsed_prediction
|
42 |
+
|
43 |
+
# Parse sentiment STS pipeline results
|
44 |
+
def parse_pipe_sts(pipe_out_text: str):
|
45 |
+
output_list = pipe_out_text
|
46 |
+
pipe_label = output_list['label']
|
47 |
+
pipe_score = float(output_list['score'])*100
|
48 |
+
|
49 |
+
parsed_prediction = 'NULL'
|
50 |
+
|
51 |
+
if pipe_label == 'NO SIMILARITY' or pipe_label == 'LABEL_0':
|
52 |
+
parsed_prediction = f'This model thinks the clauses have NO similarity. \nConfidence score of {pipe_score:.3f}%'
|
53 |
+
elif pipe_label == 'LITTLE SIMILARITY' or pipe_label == 'LABEL_1':
|
54 |
+
parsed_prediction = f'This model thinks the clauses have LITTLE similarity. \nConfidence score of {pipe_score:.3f}%'
|
55 |
+
elif pipe_label == 'MEDIUM OR HIGHER SIMILARITY' or pipe_label == 'LABEL_2':
|
56 |
+
parsed_prediction = f'This model thinks the clauses have MEDIUM to HIGH similarity. \nConfidence score of {pipe_score:.3f}%'
|
57 |
+
|
58 |
+
return parsed_prediction
|
59 |
+
|
60 |
+
#pretty sure this can be removed
|
61 |
loraModel = AutoPeftModelForSequenceClassification.from_pretrained("Intradiction/text_classification_WithLORA")
|
62 |
#tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
|
63 |
tokenizer1 = AutoTokenizer.from_pretrained("albert-base-v2")
|
|
|
99 |
|
100 |
#NLI models
|
101 |
def AlbertnoLORA_fn(text1, text2):
|
102 |
+
return parse_pipe_nli(AlbertnoLORA_pipe({'text': text1, 'text_pair': text2}))
|
103 |
|
104 |
def AlbertwithLORA_fn(text1, text2):
|
105 |
+
return parse_pipe_nli(AlbertwithLORA_pipe({'text': text1, 'text_pair': text2}))
|
106 |
|
107 |
def AlbertUntrained_fn(text1, text2):
|
108 |
+
return parse_pipe_nli(ALbertUntrained_pipe({'text': text1, 'text_pair': text2}))
|
109 |
|
110 |
|
111 |
# Handle calls to Deberta--------------------------------------------
|
|
|
121 |
|
122 |
#STS models
|
123 |
def DebertanoLORA_fn(text1, text2):
|
124 |
+
return parse_pipe_sts(DebertanoLORA_pipe({'text': text1, 'text_pair': text2}))
|
125 |
|
126 |
def DebertawithLORA_fn(text1, text2):
|
127 |
+
return parse_pipe_sts(DebertawithLORA_pipe({'text': text1, 'text_pair': text2}))
|
128 |
#return ("working2")
|
129 |
|
130 |
def DebertaUntrained_fn(text1, text2):
|
131 |
+
return parse_pipe_sts(DebertaUntrained_pipe({'text': text1, 'text_pair': text2}))
|
132 |
|
133 |
#helper functions ------------------------------------------------------
|
134 |
|
|
|
356 |
with gr.Column(variant="panel"):
|
357 |
gr.Markdown("""
|
358 |
<h2>Specifications</h2>
|
359 |
+
<p><b>Model:</b> Bert Base Uncased <br>
|
360 |
+
<b>Number of Parameters:</b> 110 Million <br>
|
361 |
<b>Dataset:</b> IMDB Movie review dataset <br>
|
362 |
<b>NLP Task:</b> Text Classification</p>
|
363 |
+
<p>Text classification is an NLP task that focuses on automatically ascribing a predefined category or labels to an input prompt. In this demonstration the Tiny Bert model has been used to classify the text on the basis of sentiment analysis, where the labels (negative and positive) will indicate the emotional state expressed by the input prompt.<br><br>The models were trained on the IMDB dataset which includes over 100k sentiment pairs pulled from IMDB movie reviews.<br><br><b>Results:</b><br> It can be seen that the LoRA fine tuned model performs comparably to the conventionally trained model. The difference arises in the training time where the conventional model takes almost 30 mins to train through 2 epochs the LoRA model takes half the time to train through 4 epochs.</p>
|
364 |
""")
|
365 |
|
366 |
with gr.Column(variant="panel"):
|
|
|
407 |
gr.Markdown("""
|
408 |
<h2>Specifications</h2>
|
409 |
<p><b>Model:</b> Albert <br>
|
410 |
+
<b>Number of Parameters:</b> 11 Million <br>
|
411 |
<b>Dataset:</b> Stanford Natural Language Inference Dataset <br>
|
412 |
+
<b>NLP Task:</b> Natural Language Inferencing</p>
|
413 |
+
<p>Natural Language Inference (NLI) which can also be referred to as Textual Entailment is an NLP task with the objective of determining the relationship between two pieces of text. Ideally to determine logical inference (i.e. If the pairs contradict or confirm one another).<br><br>The models were trained on the Stanford Natural Language Inference Dataset which is a collection of 570k human-written English sentence pairs manually labeled for balanced classification, listed as positive, negative or neutral. <br><br><b>Results</b><br>While the time to train for the conventional model may be lower if we look closer at the number of epochs the models we trained over the LoRA model has a time per epoch of 1.5 mins vs the conventional's 3mins per epoch, showing significant improvement. </p>
|
414 |
""")
|
415 |
with gr.Column(variant="panel"):
|
416 |
nli_p1 = gr.Textbox(placeholder="Prompt One",label= "Enter Query")
|
|
|
418 |
nli_btn = gr.Button("Run")
|
419 |
btnNLIStats = gr.Button("Display Training Metrics")
|
420 |
btnTensorLinkNLICon = gr.Button(value="View Conventional Training Graphs", link="https://huggingface.co/m4faisal/NLI-Conventional-Fine-Tuning/tensorboard")
|
421 |
+
btnTensorLinkNLILora = gr.Button(value="View LoRA Training Graphs", link="https://huggingface.co/m4faisal/NLI-Lora-Fine-Tuning-10K/tensorboard")
|
422 |
gr.Examples(
|
423 |
[
|
424 |
+
"A man is awake",
|
425 |
"People like apples",
|
426 |
+
"A game with mutiple people playing",
|
427 |
],
|
428 |
nli_p1,
|
429 |
label="Try asking",
|
430 |
)
|
431 |
gr.Examples(
|
432 |
[
|
433 |
+
"A man is sleeping",
|
434 |
"Apples are good",
|
435 |
+
"Some people are playing a game",
|
436 |
],
|
437 |
nli_p2,
|
438 |
label="Try asking",
|
|
|
467 |
gr.Markdown("""
|
468 |
<h2>Specifications</h2>
|
469 |
<p><b>Model:</b> Roberta Base <br>
|
470 |
+
<b>Number of Parameters:</b> 125 Million <br>
|
471 |
<b>Dataset:</b> Semantic Text Similarity Benchmark <br>
|
472 |
<b>NLP Task:</b> Semantic Text Similarity</p>
|
473 |
+
<p>Semantic text similarity measures the closeness in meaning of two pieces of text despite differences in their wording or structure. This task involves two input prompts which can be sentences, phrases or entire documents and assessing them for similarity. <br><br>This implementation uses the Roberta base model and training was performed on the semantic text similarity benchmark dataset which contains over 86k semantic pairs and their scores.<br><br><b>Results</b><br> We can see that for a comparable result the LoRA trained model manages to train for 30 epochs in 14.5 mins vs the conventional models 24 mins displaying a 60% increase in efficiency. </p>
|
474 |
""")
|
475 |
with gr.Column(variant="panel"):
|
476 |
sts_p1 = gr.Textbox(placeholder="Prompt One",label= "Enter Query")
|