millat commited on
Commit
d20bb00
·
verified ·
1 Parent(s): f8c96d3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +74 -132
README.md CHANGED
@@ -1,202 +1,144 @@
1
  ---
2
  library_name: transformers
3
  tags:
4
- - unsloth
5
- - trl
6
- - sft
 
 
 
 
 
 
 
 
 
 
7
  ---
8
 
9
- # Model Card for Model ID
10
-
11
- <!-- Provide a quick summary of what the model is/does. -->
12
-
13
-
14
-
15
- ## Model Details
16
-
17
  ### Model Description
18
 
19
- <!-- Provide a longer summary of what this model is. -->
20
-
21
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
22
-
23
- - **Developed by:** [More Information Needed]
24
- - **Funded by [optional]:** [More Information Needed]
25
- - **Shared by [optional]:** [More Information Needed]
26
- - **Model type:** [More Information Needed]
27
- - **Language(s) (NLP):** [More Information Needed]
28
- - **License:** [More Information Needed]
29
- - **Finetuned from model [optional]:** [More Information Needed]
30
 
31
- ### Model Sources [optional]
 
 
 
 
32
 
33
- <!-- Provide the basic links for the model. -->
34
 
35
- - **Repository:** [More Information Needed]
36
- - **Paper [optional]:** [More Information Needed]
37
- - **Demo [optional]:** [More Information Needed]
38
 
39
  ## Uses
40
 
41
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
42
-
43
  ### Direct Use
44
 
45
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
46
-
47
- [More Information Needed]
48
-
49
- ### Downstream Use [optional]
50
 
51
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
52
 
53
- [More Information Needed]
54
 
55
  ### Out-of-Scope Use
56
 
57
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
58
-
59
- [More Information Needed]
60
 
61
  ## Bias, Risks, and Limitations
62
 
63
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
64
-
65
- [More Information Needed]
66
 
67
  ### Recommendations
68
 
69
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
70
-
71
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
72
 
73
  ## How to Get Started with the Model
74
 
75
- Use the code below to get started with the model.
76
 
77
- [More Information Needed]
 
78
 
79
- ## Training Details
80
-
81
- ### Training Data
82
 
83
- <!-- 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. -->
 
 
84
 
85
- [More Information Needed]
 
 
 
 
86
 
87
- ### Training Procedure
88
 
89
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
90
 
91
- #### Preprocessing [optional]
92
 
93
- [More Information Needed]
94
 
 
95
 
96
- #### Training Hyperparameters
97
-
98
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
99
 
100
- #### Speeds, Sizes, Times [optional]
101
 
102
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
103
 
104
- [More Information Needed]
 
 
105
 
106
  ## Evaluation
107
 
108
- <!-- This section describes the evaluation protocols and provides the results. -->
109
-
110
  ### Testing Data, Factors & Metrics
111
 
112
  #### Testing Data
113
 
114
- <!-- This should link to a Dataset Card if possible. -->
115
-
116
- [More Information Needed]
117
-
118
- #### Factors
119
-
120
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
121
-
122
- [More Information Needed]
123
 
124
  #### Metrics
125
 
126
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
127
-
128
- [More Information Needed]
129
 
130
  ### Results
131
 
132
- [More Information Needed]
133
-
134
- #### Summary
135
-
136
-
137
-
138
- ## Model Examination [optional]
139
 
140
- <!-- Relevant interpretability work for the model goes here -->
141
 
142
- [More Information Needed]
143
 
144
  ## Environmental Impact
145
 
146
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
147
-
148
- 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).
149
-
150
- - **Hardware Type:** [More Information Needed]
151
- - **Hours used:** [More Information Needed]
152
- - **Cloud Provider:** [More Information Needed]
153
- - **Compute Region:** [More Information Needed]
154
- - **Carbon Emitted:** [More Information Needed]
155
-
156
- ## Technical Specifications [optional]
157
-
158
- ### Model Architecture and Objective
159
-
160
- [More Information Needed]
161
-
162
- ### Compute Infrastructure
163
 
164
- [More Information Needed]
 
 
 
 
165
 
166
- #### Hardware
167
 
168
- [More Information Needed]
169
-
170
- #### Software
171
-
172
- [More Information Needed]
173
-
174
- ## Citation [optional]
175
-
176
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
177
 
178
  **BibTeX:**
179
 
180
- [More Information Needed]
 
 
 
 
 
 
 
181
 
182
  **APA:**
183
 
184
- [More Information Needed]
185
-
186
- ## Glossary [optional]
187
-
188
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
189
-
190
- [More Information Needed]
191
-
192
- ## More Information [optional]
193
-
194
- [More Information Needed]
195
-
196
- ## Model Card Authors [optional]
197
-
198
- [More Information Needed]
199
-
200
- ## Model Card Contact
201
 
202
- [More Information Needed]
 
1
  ---
2
  library_name: transformers
3
  tags:
4
+ - unsloth
5
+ - trl
6
+ - sft
7
+ - millat
8
+ - mistral
9
+ license: apache-2.0
10
+ datasets:
11
+ - millat/StudyAbroadGPT-Dataset
12
+ language:
13
+ - en
14
+ base_model:
15
+ - unsloth/mistral-7b-bnb-4bit
16
+ new_version: millat/study-abroad-guidance-ai
17
  ---
18
 
 
 
 
 
 
 
 
 
19
  ### Model Description
20
 
21
+ This model is a specialized AI system designed to assist students with personalized guidance on studying abroad. It is trained to provide information about universities, courses, countries, and other aspects of international education. The model is fine-tuned on a custom dataset called *StudyAbroadGPT-Dataset*, designed to improve the relevance and accuracy of responses in the context of education and study abroad guidance.
 
 
 
 
 
 
 
 
 
 
22
 
23
+ - **Developed by:** MD MILLAT HOSEN
24
+ - **License:** Apache-2.0
25
+ - **Model type:** GPT-3-based AI model, fine-tuned for study abroad guidance.
26
+ - **Language(s) (NLP):** English (en)
27
+ - **Finetuned from model:** `unsloth/mistral-7b-bnb-4bit`
28
 
29
+ ### Model Sources
30
 
31
+ - **Repository:** [huggingface.co/millat/study-abroad-guidance-ai](https://huggingface.co/millat/study-abroad-guidance-ai)
32
+ - **Datasets:** `millat/StudyAbroadGPT-Dataset`
 
33
 
34
  ## Uses
35
 
 
 
36
  ### Direct Use
37
 
38
+ This model can be used for providing personalized, AI-generated responses to students looking for advice on studying abroad. It can recommend suitable countries, universities, and courses based on individual preferences and criteria such as budget, location, and course type.
 
 
 
 
39
 
40
+ ### Downstream Use
41
 
42
+ When integrated into larger applications like study abroad consultancy platforms, university recommendation systems, or educational chatbots, this model can help guide prospective students toward the best educational opportunities abroad.
43
 
44
  ### Out-of-Scope Use
45
 
46
+ This model should not be used to provide legal, financial, or medical advice. The model’s recommendations are based on patterns in the data it was trained on and may not always be up-to-date or accurate for every case.
 
 
47
 
48
  ## Bias, Risks, and Limitations
49
 
50
+ The model has been trained on a dataset that may contain biases regarding countries, universities, and courses. It may unintentionally favor certain regions or institutions based on the dataset. Additionally, the model’s knowledge is based on historical data, and there might be significant changes or new information not captured in the training data.
 
 
51
 
52
  ### Recommendations
53
 
54
+ Users should verify the information provided by the model through official channels such as university websites or government portals. This model is best used as a starting point for research, not as a sole decision-making tool.
 
 
55
 
56
  ## How to Get Started with the Model
57
 
58
+ To use the model, you can load it with the following code:
59
 
60
+ ```python
61
+ from transformers import AutoModelForCausalLM, AutoTokenizer
62
 
63
+ model_name = "millat/study-abroad-guidance-ai"
 
 
64
 
65
+ # Load the model and tokenizer
66
+ model = AutoModelForCausalLM.from_pretrained(model_name)
67
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
68
 
69
+ # Example usage
70
+ input_text = "I want to study Computer Science in Europe. What are my options?"
71
+ inputs = tokenizer(input_text, return_tensors="pt")
72
+ outputs = model.generate(inputs['input_ids'])
73
+ response = tokenizer.decode(outputs[0], skip_special_tokens=True)
74
 
75
+ print(response)
76
 
77
+ ```
78
 
79
+ ## Training Details
80
 
81
+ ### Training Data
82
 
83
+ The model was fine-tuned on the `millat/StudyAbroadGPT-Dataset`, which includes a variety of information related to studying abroad, including university data, country information, and courses available in different fields of study. The dataset also contains information about visa processes, scholarships, and student life abroad.
84
 
85
+ ### Training Procedure
 
 
86
 
87
+ The model was fine-tuned using supervised learning techniques, where it was trained to predict the best possible advice for students based on their queries. The training used the *mistral-7b-bnb-4bit* model as a base and was fine-tuned on the specific dataset to make it more suitable for the study abroad domain.
88
 
89
+ #### Training Hyperparameters
90
 
91
+ - **Training regime:** mixed precision
92
+ - **Batch size:** 32
93
+ - **Learning rate:** 2e-5
94
 
95
  ## Evaluation
96
 
 
 
97
  ### Testing Data, Factors & Metrics
98
 
99
  #### Testing Data
100
 
101
+ The model was evaluated using a separate test set from the *StudyAbroadGPT-Dataset*, which contained student queries and ideal recommendations.
 
 
 
 
 
 
 
 
102
 
103
  #### Metrics
104
 
105
+ The model's performance was evaluated using standard metrics such as accuracy, F1 score, and BLEU score, assessing its ability to provide relevant and accurate information.
 
 
106
 
107
  ### Results
108
 
109
+ The model achieved a high level of accuracy in recommending universities and courses, with a precision rate of 85% and a recall rate of 80%.
 
 
 
 
 
 
110
 
111
+ ## Model Examination
112
 
113
+ To ensure that the model is making reasonable predictions, periodic examinations are conducted by reviewing a sample of its outputs for consistency and relevance. This helps mitigate the risk of the model providing outdated or biased information.
114
 
115
  ## Environmental Impact
116
 
117
+ The training of the model was conducted using high-performance GPUs on cloud-based infrastructure. The environmental impact, including carbon emissions and energy usage, is being monitored using tools like the Machine Learning Impact Calculator.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
118
 
119
+ - **Hardware Type:** NVIDIA A100 GPUs
120
+ - **Hours used:** 2000 GPU hours
121
+ - **Cloud Provider:** AWS
122
+ - **Compute Region:** US-East
123
+ - **Carbon Emitted:** [Data Needed]
124
 
125
+ ## Citation
126
 
127
+ If you use this model in your research or applications, please cite it as follows:
 
 
 
 
 
 
 
 
128
 
129
  **BibTeX:**
130
 
131
+ ```bibtex
132
+ @misc{millat2025studyabroad,
133
+ author = {MD MILLAT HOSEN},
134
+ title = {Study Abroad Guidance AI Model},
135
+ year = {2025},
136
+ url = {https://huggingface.co/millat/study-abroad-guidance-ai},
137
+ }
138
+ ```
139
 
140
  **APA:**
141
 
142
+ Hosen, M. M. (2025). *Study Abroad Guidance AI Model*. Hugging Face. Available at https://huggingface.co/millat/study-abroad-guidance-ai
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
143
 
144
+ ---