Commit
•
257e5a2
1
Parent(s):
32354a0
Update README.md
Browse files
README.md
CHANGED
@@ -6,197 +6,111 @@ tags:
|
|
6 |
|
7 |
# Model Card for Model ID
|
8 |
|
9 |
-
|
10 |
|
11 |
|
12 |
|
13 |
-
##
|
14 |
|
15 |
-
|
16 |
|
17 |
-
|
|
|
|
|
18 |
|
19 |
-
|
|
|
20 |
|
21 |
-
- **Developed by:** [More Information Needed]
|
22 |
-
- **Funded by [optional]:** [More Information Needed]
|
23 |
-
- **Shared by [optional]:** [More Information Needed]
|
24 |
-
- **Model type:** [More Information Needed]
|
25 |
-
- **Language(s) (NLP):** [More Information Needed]
|
26 |
-
- **License:** [More Information Needed]
|
27 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
28 |
|
29 |
-
### Model Sources [optional]
|
30 |
|
31 |
-
<!-- Provide the basic links for the model. -->
|
32 |
|
33 |
-
- **Repository:** [More Information Needed]
|
34 |
-
- **Paper [optional]:** [More Information Needed]
|
35 |
-
- **Demo [optional]:** [More Information Needed]
|
36 |
|
37 |
-
## Uses
|
38 |
|
39 |
-
|
40 |
|
41 |
-
###
|
|
|
|
|
|
|
|
|
42 |
|
43 |
-
|
|
|
|
|
44 |
|
45 |
-
|
46 |
|
47 |
-
###
|
|
|
48 |
|
49 |
-
|
|
|
50 |
|
51 |
-
|
|
|
52 |
|
53 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
|
55 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
56 |
|
57 |
-
|
|
|
|
|
58 |
|
59 |
-
|
|
|
|
|
|
|
60 |
|
61 |
-
|
|
|
|
|
|
|
62 |
|
63 |
-
|
64 |
|
65 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
|
67 |
-
|
|
|
68 |
|
69 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
70 |
|
71 |
-
## How to Get Started with the Model
|
72 |
|
73 |
-
Use the code below to get started with the model.
|
74 |
|
75 |
-
[More Information Needed]
|
76 |
|
77 |
-
|
78 |
|
79 |
-
### Training Data
|
80 |
|
81 |
-
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
82 |
-
|
83 |
-
[More Information Needed]
|
84 |
-
|
85 |
-
### Training Procedure
|
86 |
-
|
87 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
88 |
-
|
89 |
-
#### Preprocessing [optional]
|
90 |
-
|
91 |
-
[More Information Needed]
|
92 |
-
|
93 |
-
|
94 |
-
#### Training Hyperparameters
|
95 |
-
|
96 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
97 |
-
|
98 |
-
#### Speeds, Sizes, Times [optional]
|
99 |
-
|
100 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
101 |
-
|
102 |
-
[More Information Needed]
|
103 |
-
|
104 |
-
## Evaluation
|
105 |
-
|
106 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
107 |
-
|
108 |
-
### Testing Data, Factors & Metrics
|
109 |
-
|
110 |
-
#### Testing Data
|
111 |
-
|
112 |
-
<!-- This should link to a Dataset Card if possible. -->
|
113 |
-
|
114 |
-
[More Information Needed]
|
115 |
-
|
116 |
-
#### Factors
|
117 |
-
|
118 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
119 |
-
|
120 |
-
[More Information Needed]
|
121 |
-
|
122 |
-
#### Metrics
|
123 |
-
|
124 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
125 |
-
|
126 |
-
[More Information Needed]
|
127 |
-
|
128 |
-
### Results
|
129 |
-
|
130 |
-
[More Information Needed]
|
131 |
-
|
132 |
-
#### Summary
|
133 |
-
|
134 |
-
|
135 |
-
|
136 |
-
## Model Examination [optional]
|
137 |
-
|
138 |
-
<!-- Relevant interpretability work for the model goes here -->
|
139 |
-
|
140 |
-
[More Information Needed]
|
141 |
-
|
142 |
-
## Environmental Impact
|
143 |
-
|
144 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
145 |
-
|
146 |
-
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
147 |
-
|
148 |
-
- **Hardware Type:** [More Information Needed]
|
149 |
-
- **Hours used:** [More Information Needed]
|
150 |
-
- **Cloud Provider:** [More Information Needed]
|
151 |
-
- **Compute Region:** [More Information Needed]
|
152 |
-
- **Carbon Emitted:** [More Information Needed]
|
153 |
-
|
154 |
-
## Technical Specifications [optional]
|
155 |
-
|
156 |
-
### Model Architecture and Objective
|
157 |
-
|
158 |
-
[More Information Needed]
|
159 |
-
|
160 |
-
### Compute Infrastructure
|
161 |
-
|
162 |
-
[More Information Needed]
|
163 |
-
|
164 |
-
#### Hardware
|
165 |
-
|
166 |
-
[More Information Needed]
|
167 |
-
|
168 |
-
#### Software
|
169 |
-
|
170 |
-
[More Information Needed]
|
171 |
-
|
172 |
-
## Citation [optional]
|
173 |
-
|
174 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
175 |
-
|
176 |
-
**BibTeX:**
|
177 |
-
|
178 |
-
[More Information Needed]
|
179 |
-
|
180 |
-
**APA:**
|
181 |
-
|
182 |
-
[More Information Needed]
|
183 |
-
|
184 |
-
## Glossary [optional]
|
185 |
-
|
186 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
187 |
-
|
188 |
-
[More Information Needed]
|
189 |
-
|
190 |
-
## More Information [optional]
|
191 |
-
|
192 |
-
[More Information Needed]
|
193 |
-
|
194 |
-
## Model Card Authors [optional]
|
195 |
-
|
196 |
-
[More Information Needed]
|
197 |
-
|
198 |
-
## Model Card Contact
|
199 |
-
|
200 |
-
[More Information Needed]
|
201 |
|
202 |
|
|
|
6 |
|
7 |
# Model Card for Model ID
|
8 |
|
9 |
+
This a Mistral 7b Quantized trained on Academic Short QA model . It is fine tuned using Qlora technique and it is trainde till around 500 step with loss around 0.450
|
10 |
|
11 |
|
12 |
|
13 |
+
## Requirements
|
14 |
|
15 |
+
```python
|
16 |
|
17 |
+
!pip install gradio
|
18 |
+
!pip install -U xformers --index-url https://download.pytorch.org/whl/cu121
|
19 |
+
!pip install "unsloth[kaggle-new] @ git+https://github.com/unslothai/unsloth.git"
|
20 |
|
21 |
+
import os
|
22 |
+
os.environ["WANDB_DISABLED"] = "true"
|
23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
24 |
|
|
|
25 |
|
|
|
26 |
|
|
|
|
|
|
|
27 |
|
|
|
28 |
|
29 |
+
```
|
30 |
|
31 |
+
### Gradio App
|
32 |
+
```python
|
33 |
+
import gradio as gr
|
34 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
35 |
+
import re
|
36 |
|
37 |
+
model_id = "DisgustingOzil/Academic-ShortQA-Generator"
|
38 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
39 |
+
model = AutoModelForCausalLM.from_pretrained(model_id)
|
40 |
|
41 |
+
alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
|
42 |
|
43 |
+
### Instruction:
|
44 |
+
{}
|
45 |
|
46 |
+
### Input:
|
47 |
+
{}
|
48 |
|
49 |
+
### Response:
|
50 |
+
{}"""
|
51 |
|
52 |
+
def partition_text(text, partition_size):
|
53 |
+
words = text.split()
|
54 |
+
total_words = len(words)
|
55 |
+
words_per_partition = total_words // partition_size
|
56 |
+
partitions = []
|
57 |
+
for i in range(0, total_words, words_per_partition):
|
58 |
+
partition = " ".join(words[i:i+words_per_partition])
|
59 |
+
if len(partition) > 100: # Ensuring meaningful length for MCQ generation
|
60 |
+
partitions.append(partition)
|
61 |
+
return partitions
|
62 |
|
63 |
+
def generate_mcqs_for_partition(Instruction, partition, temperature, top_k):
|
64 |
+
inputs = tokenizer(alpaca_prompt.format(Instruction, partition, ""), return_tensors="pt")
|
65 |
+
outputs = model.generate(
|
66 |
+
**inputs,
|
67 |
+
max_length=512,
|
68 |
+
num_return_sequences=1,
|
69 |
+
temperature=temperature,
|
70 |
+
top_k=top_k
|
71 |
+
)
|
72 |
+
output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
73 |
+
return output_text
|
74 |
|
75 |
+
def generate_mcqs(Instruction, text, partition_count, temperature, top_k):
|
76 |
+
partitions = partition_text(text, partition_count)
|
77 |
+
mcqs_output = []
|
78 |
|
79 |
+
for part in partitions:
|
80 |
+
output_text = generate_mcqs_for_partition(Instruction, part, temperature, top_k)
|
81 |
+
pattern = r'<question>(.*?)</question>.*?<answer>(.*?)</answer>'
|
82 |
+
matches = re.findall(pattern, output_text, re.DOTALL)
|
83 |
|
84 |
+
for match in matches:
|
85 |
+
question = match[0].strip()
|
86 |
+
correct_answer = match[1].strip()
|
87 |
+
mcqs_output.append(f"Question: {question}\nCorrect Answer: {correct_answer}\n")
|
88 |
|
89 |
+
return "\n".join(mcqs_output) if mcqs_output else "No MCQs could be generated from the input."
|
90 |
|
91 |
+
iface = gr.Interface(
|
92 |
+
fn=generate_mcqs,
|
93 |
+
inputs=[
|
94 |
+
gr.Textbox(label="Instruction"),
|
95 |
+
gr.Textbox(lines=10, label="Input Biology Text"),
|
96 |
+
gr.Slider(minimum=1, maximum=10, step=1, label="Partition Count"),
|
97 |
+
gr.Slider(minimum=0.5, maximum=1.0, step=0.05 , label="Temperature"),
|
98 |
+
gr.Slider(minimum=1, maximum=50, step=1, label="Top K")
|
99 |
+
],
|
100 |
+
outputs="text",
|
101 |
+
title="ShortQA Generator",
|
102 |
+
description="Enter a text about Biology to generate MCQs. Adjust the sliders to change the model's generation parameters."
|
103 |
+
)
|
104 |
|
105 |
+
if __name__ == "__main__":
|
106 |
+
iface.launch(debug=True, share=True)
|
107 |
|
|
|
108 |
|
|
|
109 |
|
|
|
110 |
|
|
|
111 |
|
112 |
+
```
|
113 |
|
|
|
114 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
115 |
|
116 |
|