Update README.md
Browse files
README.md
CHANGED
@@ -1,205 +1,99 @@
|
|
1 |
-
---
|
2 |
license: apache-2.0
|
3 |
language:
|
4 |
- en
|
5 |
metrics:
|
6 |
-
-
|
7 |
base_model:
|
8 |
- microsoft/phi-2
|
9 |
pipeline_tag: question-answering
|
10 |
library_name: fastai
|
11 |
---
|
12 |
-
# Model Card for Model
|
13 |
-
|
14 |
-
<!-- Provide a quick summary of what the model is/does. -->
|
15 |
|
16 |
-
This
|
17 |
|
18 |
## Model Details
|
19 |
|
20 |
### Model Description
|
21 |
|
22 |
-
|
23 |
-
|
|
|
|
|
|
|
24 |
|
|
|
25 |
|
26 |
-
|
27 |
-
- **Funded by [optional]:** [More Information Needed]
|
28 |
-
- **Shared by [optional]:** [More Information Needed]
|
29 |
-
- **Model type:** [More Information Needed]
|
30 |
-
- **Language(s) (NLP):** [More Information Needed]
|
31 |
-
- **License:** [More Information Needed]
|
32 |
-
- **Finetuned from model [optional]:** [More Information Needed]
|
33 |
|
34 |
-
### Model Sources
|
35 |
|
36 |
-
|
|
|
|
|
37 |
|
38 |
-
|
39 |
-
- **Paper [optional]:** [More Information Needed]
|
40 |
-
- **Demo [optional]:** [More Information Needed]
|
41 |
|
42 |
## Uses
|
43 |
|
44 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
45 |
-
|
46 |
### Direct Use
|
|
|
47 |
|
48 |
-
|
49 |
-
|
50 |
-
[More Information Needed]
|
51 |
-
|
52 |
-
### Downstream Use [optional]
|
53 |
-
|
54 |
-
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
55 |
-
|
56 |
-
[More Information Needed]
|
57 |
|
58 |
### Out-of-Scope Use
|
|
|
59 |
|
60 |
-
|
61 |
-
|
62 |
-
[More Information Needed]
|
63 |
|
64 |
## Bias, Risks, and Limitations
|
65 |
|
66 |
-
|
67 |
-
|
68 |
-
|
69 |
-
|
70 |
-
### Recommendations
|
71 |
|
72 |
-
|
73 |
-
|
74 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
75 |
|
76 |
## How to Get Started with the Model
|
77 |
|
78 |
-
|
79 |
-
|
80 |
-
[More Information Needed]
|
81 |
-
|
82 |
-
## Training Details
|
83 |
-
|
84 |
-
### Training Data
|
85 |
-
|
86 |
-
<!-- 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. -->
|
87 |
-
|
88 |
-
[More Information Needed]
|
89 |
-
|
90 |
-
### Training Procedure
|
91 |
-
|
92 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
93 |
-
|
94 |
-
#### Preprocessing [optional]
|
95 |
-
|
96 |
-
[More Information Needed]
|
97 |
-
|
98 |
-
|
99 |
-
#### Training Hyperparameters
|
100 |
-
|
101 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
102 |
-
|
103 |
-
#### Speeds, Sizes, Times [optional]
|
104 |
-
|
105 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
106 |
-
|
107 |
-
[More Information Needed]
|
108 |
-
|
109 |
-
## Evaluation
|
110 |
-
|
111 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
112 |
-
|
113 |
-
### Testing Data, Factors & Metrics
|
114 |
-
|
115 |
-
#### Testing Data
|
116 |
|
117 |
-
|
|
|
|
|
118 |
|
119 |
-
|
|
|
120 |
|
121 |
-
#### Factors
|
122 |
|
123 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
124 |
|
125 |
-
|
126 |
|
127 |
-
|
128 |
|
129 |
-
|
130 |
-
|
131 |
-
[More Information Needed]
|
132 |
-
|
133 |
-
### Results
|
134 |
-
|
135 |
-
[More Information Needed]
|
136 |
-
|
137 |
-
#### Summary
|
138 |
-
|
139 |
-
|
140 |
-
|
141 |
-
## Model Examination [optional]
|
142 |
-
|
143 |
-
<!-- Relevant interpretability work for the model goes here -->
|
144 |
-
|
145 |
-
[More Information Needed]
|
146 |
-
|
147 |
-
## Environmental Impact
|
148 |
-
|
149 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
150 |
-
|
151 |
-
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).
|
152 |
-
|
153 |
-
- **Hardware Type:** [More Information Needed]
|
154 |
-
- **Hours used:** [More Information Needed]
|
155 |
-
- **Cloud Provider:** [More Information Needed]
|
156 |
-
- **Compute Region:** [More Information Needed]
|
157 |
-
- **Carbon Emitted:** [More Information Needed]
|
158 |
-
|
159 |
-
## Technical Specifications [optional]
|
160 |
-
|
161 |
-
### Model Architecture and Objective
|
162 |
-
|
163 |
-
[More Information Needed]
|
164 |
-
|
165 |
-
### Compute Infrastructure
|
166 |
-
|
167 |
-
[More Information Needed]
|
168 |
-
|
169 |
-
#### Hardware
|
170 |
-
|
171 |
-
[More Information Needed]
|
172 |
-
|
173 |
-
#### Software
|
174 |
-
|
175 |
-
[More Information Needed]
|
176 |
-
|
177 |
-
## Citation [optional]
|
178 |
-
|
179 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
180 |
-
|
181 |
-
**BibTeX:**
|
182 |
-
|
183 |
-
[More Information Needed]
|
184 |
-
|
185 |
-
**APA:**
|
186 |
-
|
187 |
-
[More Information Needed]
|
188 |
-
|
189 |
-
## Glossary [optional]
|
190 |
-
|
191 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
192 |
-
|
193 |
-
[More Information Needed]
|
194 |
-
|
195 |
-
## More Information [optional]
|
196 |
-
|
197 |
-
[More Information Needed]
|
198 |
|
199 |
-
##
|
200 |
|
201 |
-
|
202 |
|
203 |
-
|
|
|
|
|
|
|
|
|
|
|
204 |
|
205 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
license: apache-2.0
|
2 |
language:
|
3 |
- en
|
4 |
metrics:
|
5 |
+
- rouge
|
6 |
base_model:
|
7 |
- microsoft/phi-2
|
8 |
pipeline_tag: question-answering
|
9 |
library_name: fastai
|
10 |
---
|
11 |
+
# Model Card for PEFT-Fine-Tuned Model
|
|
|
|
|
12 |
|
13 |
+
This model card documents a PEFT-fine-tuned version of `microsoft/phi-2` for question-answering tasks. The PEFT fine-tuning improved the model's performance, as detailed in the evaluation section.
|
14 |
|
15 |
## Model Details
|
16 |
|
17 |
### Model Description
|
18 |
|
19 |
+
- **Developed by:** JamieAi33
|
20 |
+
- **Finetuned from model:** `microsoft/phi-2`
|
21 |
+
- **Model type:** PEFT fine-tuned transformer
|
22 |
+
- **Language(s) (NLP):** English
|
23 |
+
- **License:** Apache 2.0
|
24 |
|
25 |
+
The base model `microsoft/phi-2` was adapted using Parameter-Efficient Fine-Tuning (PEFT) for question-answering tasks. The training process focused on improving performance metrics while keeping computational costs low.
|
26 |
|
27 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
|
29 |
+
### Model Sources
|
30 |
|
31 |
+
- **Repository:** https://huggingface.co/JamieAi33/Phi-2-QLora
|
32 |
+
- **Paper:** [Optional: Add a reference to PEFT or any relevant paper]
|
33 |
+
- **Demo:** [Optional: Link to your Hugging Face Space or demo]
|
34 |
|
35 |
+
---
|
|
|
|
|
36 |
|
37 |
## Uses
|
38 |
|
|
|
|
|
39 |
### Direct Use
|
40 |
+
This model can be used out-of-the-box for question-answering tasks.
|
41 |
|
42 |
+
### Downstream Use
|
43 |
+
The model can be fine-tuned further on domain-specific datasets for improved performance.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
44 |
|
45 |
### Out-of-Scope Use
|
46 |
+
Avoid using this model for tasks outside question-answering or where fairness, bias, and ethical considerations are critical without further validation.
|
47 |
|
48 |
+
---
|
|
|
|
|
49 |
|
50 |
## Bias, Risks, and Limitations
|
51 |
|
52 |
+
Users should be aware that:
|
53 |
+
- The model is trained on publicly available data and may inherit biases present in the training data.
|
54 |
+
- It is optimized for English and may perform poorly in other languages.
|
|
|
|
|
55 |
|
56 |
+
---
|
|
|
|
|
57 |
|
58 |
## How to Get Started with the Model
|
59 |
|
60 |
+
Here鈥檚 an example of loading the model:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
61 |
|
62 |
+
```python
|
63 |
+
from transformers import AutoModel
|
64 |
+
from peft import PeftModel
|
65 |
|
66 |
+
base_model = AutoModel.from_pretrained("microsoft/phi-2")
|
67 |
+
adapter_model = PeftModel.from_pretrained(base_model, "JamieAi33/Phi-2-QLora")
|
68 |
|
|
|
69 |
|
|
|
70 |
|
71 |
+
# Model Name: PEFT Fine-Tuned `microsoft/phi-2`
|
72 |
|
73 |
+
This repository contains a PEFT fine-tuned version of the `microsoft/phi-2` model for question-answering tasks. The fine-tuning process leveraged Parameter-Efficient Fine-Tuning (PEFT) techniques to achieve improved performance.
|
74 |
|
75 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
|
77 |
+
## Metrics
|
78 |
|
79 |
+
The model's performance was evaluated using the ROUGE metric. Below are the results:
|
80 |
|
81 |
+
| **Metric** | **Original Model** | **PEFT Model** | **Absolute Improvement** |
|
82 |
+
|-----------------|--------------------|----------------|---------------------------|
|
83 |
+
| **ROUGE-1** | 29.76% | 44.51% | +14.75% |
|
84 |
+
| **ROUGE-2** | 10.76% | 15.68% | +4.92% |
|
85 |
+
| **ROUGE-L** | 21.69% | 30.95% | +9.25% |
|
86 |
+
| **ROUGE-Lsum** | 22.75% | 31.49% | +8.74% |
|
87 |
|
88 |
+
---
|
89 |
+
## Training Configuration
|
90 |
+
|
91 |
+
| Hyperparameter | Value |
|
92 |
+
|-----------------------|-------------------------|
|
93 |
+
| **Batch Size** | 1 |
|
94 |
+
| **Learning Rate** | 2e-4 |
|
95 |
+
| **Max Steps** | 1000 |
|
96 |
+
| **Optimizer** | Paged AdamW (8-bit) |
|
97 |
+
| **Logging Steps** | 25 |
|
98 |
+
| **Evaluation Steps** | 25 |
|
99 |
+
| **Gradient Checkpointing** | Enabled |
|