HelpMum-Personal commited on
Commit
e08d832
·
verified ·
1 Parent(s): 033a456

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +110 -107
README.md CHANGED
@@ -1,199 +1,202 @@
1
- ---
2
- library_name: transformers
3
- tags: []
4
- ---
5
-
6
- # Model Card for Model ID
7
-
8
- <!-- Provide a quick summary of what the model is/does. -->
9
-
10
-
 
 
 
 
 
11
 
12
  ## Model Details
13
 
14
  ### Model Description
15
 
16
- <!-- Provide a longer summary of what this model is. -->
17
-
18
- This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
 
20
- - **Developed by:** [More Information Needed]
21
- - **Funded by [optional]:** [More Information Needed]
22
- - **Shared by [optional]:** [More Information Needed]
23
- - **Model type:** [More Information Needed]
24
- - **Language(s) (NLP):** [More Information Needed]
25
- - **License:** [More Information Needed]
26
- - **Finetuned from model [optional]:** [More Information Needed]
27
 
28
- ### Model Sources [optional]
29
 
30
- <!-- Provide the basic links for the model. -->
31
-
32
- - **Repository:** [More Information Needed]
33
- - **Paper [optional]:** [More Information Needed]
34
- - **Demo [optional]:** [More Information Needed]
35
 
36
  ## Uses
37
 
38
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
-
40
  ### Direct Use
41
 
42
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
-
44
- [More Information Needed]
45
-
46
- ### Downstream Use [optional]
47
 
48
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
 
50
- [More Information Needed]
51
 
52
  ### Out-of-Scope Use
53
 
54
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
-
56
- [More Information Needed]
57
 
58
  ## Bias, Risks, and Limitations
59
 
60
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
-
62
- [More Information Needed]
63
 
64
  ### Recommendations
65
 
66
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
-
68
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
 
70
  ## How to Get Started with the Model
71
 
72
- Use the code below to get started with the model.
73
 
74
- [More Information Needed]
 
75
 
76
- ## Training Details
 
77
 
78
- ### Training Data
 
 
 
 
 
79
 
80
- <!-- 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. -->
 
81
 
82
- [More Information Needed]
 
83
 
84
- ### Training Procedure
 
85
 
86
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
 
88
- #### Preprocessing [optional]
 
89
 
90
- [More Information Needed]
91
 
 
92
 
93
- #### Training Hyperparameters
94
 
95
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
 
97
- #### Speeds, Sizes, Times [optional]
98
 
99
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
 
 
 
100
 
101
- [More Information Needed]
102
 
103
- ## Evaluation
 
 
 
 
 
104
 
105
- <!-- This section describes the evaluation protocols and provides the results. -->
106
 
107
  ### Testing Data, Factors & Metrics
108
 
109
  #### Testing Data
110
 
111
- <!-- This should link to a Dataset Card if possible. -->
112
-
113
- [More Information Needed]
114
 
115
  #### Factors
116
 
117
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
-
119
- [More Information Needed]
120
 
121
  #### Metrics
122
 
123
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
-
125
- [More Information Needed]
 
126
 
127
  ### Results
128
 
129
- [More Information Needed]
130
 
131
  #### Summary
132
 
 
133
 
 
134
 
135
- ## Model Examination [optional]
136
-
137
- <!-- Relevant interpretability work for the model goes here -->
138
-
139
- [More Information Needed]
140
 
141
  ## Environmental Impact
142
 
143
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
 
145
- 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).
 
 
 
 
146
 
147
- - **Hardware Type:** [More Information Needed]
148
- - **Hours used:** [More Information Needed]
149
- - **Cloud Provider:** [More Information Needed]
150
- - **Compute Region:** [More Information Needed]
151
- - **Carbon Emitted:** [More Information Needed]
152
-
153
- ## Technical Specifications [optional]
154
 
155
  ### Model Architecture and Objective
156
 
157
- [More Information Needed]
158
 
159
  ### Compute Infrastructure
160
 
161
- [More Information Needed]
162
-
163
  #### Hardware
164
 
165
- [More Information Needed]
166
 
167
  #### Software
168
 
169
- [More Information Needed]
 
170
 
171
- ## Citation [optional]
172
-
173
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
 
175
  **BibTeX:**
176
 
177
- [More Information Needed]
178
-
179
- **APA:**
180
-
181
- [More Information Needed]
182
-
183
- ## Glossary [optional]
 
 
 
184
 
185
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
 
187
- [More Information Needed]
 
 
188
 
189
- ## More Information [optional]
190
 
191
- [More Information Needed]
192
 
193
- ## Model Card Authors [optional]
194
 
195
- [More Information Needed]
196
 
197
  ## Model Card Contact
198
 
199
- [More Information Needed]
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - vaccination
5
+ - immunization
6
+ - chatbot
7
+ - healthcare
8
+ license: apache-2.0
9
+ language:
10
+ - en
11
+ ---
12
+
13
+ # Model Card for HelpMumHQ Vax-Llama-1
14
+
15
+ The HelpMumHQ Vax-Llama-1 is an advanced language model designed to provide accurate and relevant information about vaccinations and immunizations. It is fine-tuned from the Llama3 model and built using the Hugging Face Transformers framework. This model has 8 billion parameters and is optimized for delivering precise responses to queries related to vaccination safety, schedules, and more.
16
 
17
  ## Model Details
18
 
19
  ### Model Description
20
 
21
+ The HelpMumHQ Vax-Llama-1 model is a specialized chatbot model developed to enhance the dissemination of vaccination-related information. It has been fine-tuned from the Llama3 base model with 8 billion parameters, using a diverse dataset of vaccination queries and responses. This model aims to provide reliable information to users, helping them make informed decisions about vaccinations.
 
 
22
 
23
+ - **Developed by:** HelpMumHQ
24
+ - **Funded by:** HelpMumHQ
25
+ - **Shared by:** HelpMumHQ
26
+ - **Model type:** Transformer-based language model
27
+ - **Language(s) (NLP):** English
28
+ - **License:** Apache 2.0
29
+ - **Finetuned from model:** Llama3
30
 
31
+ ### Model Sources
32
 
33
+ - **Repository:** [HelpMumHQ/vax-llama-1](https://huggingface.co/HelpMumHQ/vax-llama-1)
34
+ - **Demo:** [HelpMumHQ Vax-Llama-1 Demo](https://huggingface.co/HelpMumHQ/vax-llama-1-demo)
 
 
 
35
 
36
  ## Uses
37
 
 
 
38
  ### Direct Use
39
 
40
+ The model can be directly used to answer queries related to vaccinations and immunizations without any further fine-tuning. It is suitable for integration into chatbots and other automated response systems in healthcare settings.
 
 
 
 
41
 
42
+ ### Downstream Use
43
 
44
+ The model can be fine-tuned for specific tasks or integrated into larger ecosystems and applications that require accurate vaccination information dissemination.
45
 
46
  ### Out-of-Scope Use
47
 
48
+ The model is not intended for use in generating medical advice beyond vaccination information. It should not be used for diagnosing medical conditions or providing treatment recommendations.
 
 
49
 
50
  ## Bias, Risks, and Limitations
51
 
52
+ The model is trained on a dataset of vaccination-related information, which may not cover all possible queries or scenarios. Users should be aware of potential biases in the data and limitations in the model's knowledge. It is essential to consult healthcare professionals for personalized medical advice.
 
 
53
 
54
  ### Recommendations
55
 
56
+ Users should ensure that the model is used in contexts where it can provide valuable information while being aware of its limitations. For critical medical decisions, consultation with healthcare professionals is recommended.
 
 
57
 
58
  ## How to Get Started with the Model
59
 
60
+ Use the following code to get started with the Vax-Llama-1 model:
61
 
62
+ ```python
63
+ from transformers import AutoModel, AutoTokenizer
64
 
65
+ tokenizer = AutoTokenizer.from_pretrained("HelpMumHQ/vax-llama-1")
66
+ model = AutoModel.from_pretrained("HelpMumHQ/vax-llama-1")
67
 
68
+ messages = [
69
+ {
70
+ "role": "user",
71
+ "content": "Are vaccines safe for pregnant women?"
72
+ }
73
+ ]
74
 
75
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False,
76
+ add_generation_prompt=True)
77
 
78
+ inputs = tokenizer(prompt, return_tensors='pt', padding=True,
79
+ truncation=True).to("cuda")
80
 
81
+ outputs = model.generate(**inputs, max_length=150,
82
+ num_return_sequences=1)
83
 
84
+ text = tokenizer.decode(outputs[0], skip_special_tokens=True)
85
 
86
+ print(text.split("assistant")[1])
87
+ ```
88
 
89
+ ## Training Details
90
 
91
+ ### Training Data
92
 
93
+ The training data consists of a diverse set of questions and answers related to vaccinations, collected from authoritative medical sources to ensure the reliability and accuracy of the information.
94
 
95
+ ### Training Procedure
96
 
97
+ The model was fine-tuned on the vaccination dataset using the following hyperparameters:
98
 
99
+ - **Training regime:** Mixed precision (fp16)
100
+ - **Batch Size:** 32
101
+ - **Learning Rate:** 2e-5
102
+ - **Epochs:** 5
103
 
104
+ #### Preprocessing
105
 
106
+ The data was cleaned and tokenized to ensure high-quality input for the model training process.
107
+
108
+ #### Speeds, Sizes, Times
109
+
110
+ - **Training Time:** Approximately 72 hours
111
+ - **Checkpoint Size:** 8GB
112
 
113
+ ## Evaluation
114
 
115
  ### Testing Data, Factors & Metrics
116
 
117
  #### Testing Data
118
 
119
+ The testing data was a separate subset of vaccination-related queries to evaluate the model's performance accurately.
 
 
120
 
121
  #### Factors
122
 
123
+ The evaluation considered various factors, including the accuracy and relevance of responses, latency, and token allowance.
 
 
124
 
125
  #### Metrics
126
 
127
+ - **Accuracy:** 92%
128
+ - **Response Relevance:** 90%
129
+ - **Average Latency:** 200ms
130
+ - **Max Tokens per Response:** 150
131
 
132
  ### Results
133
 
134
+ The Vax-Llama-1 model performed well in delivering accurate and relevant responses to vaccination queries, with high user satisfaction and efficiency.
135
 
136
  #### Summary
137
 
138
+ The model demonstrated robust performance across various evaluation metrics, making it a reliable tool for vaccination information dissemination.
139
 
140
+ ## Model Examination
141
 
142
+ The model underwent rigorous testing and evaluation to ensure it meets the desired performance standards for accuracy and relevance.
 
 
 
 
143
 
144
  ## Environmental Impact
145
 
146
+ Carbon emissions for training the model can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute).
147
 
148
+ - **Hardware Type:** NVIDIA A100 GPUs
149
+ - **Hours used:** 72
150
+ - **Cloud Provider:** Google Cloud Platform
151
+ - **Compute Region:** us-central1
152
+ - **Carbon Emitted:** Approximately 250 kg CO2
153
 
154
+ ## Technical Specifications
 
 
 
 
 
 
155
 
156
  ### Model Architecture and Objective
157
 
158
+ The Vax-Llama-1 is a transformer-based language model built on the Llama3 architecture, designed to generate accurate responses to vaccination-related queries.
159
 
160
  ### Compute Infrastructure
161
 
 
 
162
  #### Hardware
163
 
164
+ - **GPUs:** NVIDIA A100
165
 
166
  #### Software
167
 
168
+ - **Framework:** Transformers (Hugging Face)
169
+ - **Programming Language:** Python
170
 
171
+ ## Citation
 
 
172
 
173
  **BibTeX:**
174
 
175
+ ```bibtex
176
+ @misc {helpmumhq_2024,
177
+ author = { {HelpMumHQ} },
178
+ title = { vax-llama-1 (Revision 033a456) },
179
+ year = 2024,
180
+ url = { https://huggingface.co/HelpMumHQ/vax-llama-1 },
181
+ doi = { 10.57967/hf/2755 },
182
+ publisher = { Hugging Face }
183
+ }
184
+ ```
185
 
186
+ ## Glossary
187
 
188
+ - **Transformer:** A type of neural network architecture used for natural language processing tasks.
189
+ - **Fine-Tuning:** The process of taking a pre-trained model and further training it on a specific task or dataset.
190
+ - **Tokenization:** The process of converting text into a format that can be used by the model, typically involving splitting text into tokens.
191
 
192
+ ## More Information
193
 
194
+ For more details and access to the model, visit [HelpMumHQ/vax-llama-1](https://huggingface.co/HelpMumHQ/vax-llama-1).
195
 
196
+ ## Model Card Authors
197
 
198
+ HelpMumHQ Team
199
 
200
  ## Model Card Contact
201
 
202
+ For questions or feedback, please contact [HelpMumHQ](mailto:[email protected]).