deepanshupillm commited on
Commit
723f8bd
·
verified ·
1 Parent(s): 6fd86f3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +125 -119
README.md CHANGED
@@ -18,122 +18,128 @@ tags:
18
  ---
19
  **model_name: 169Pi/generic_slm**
20
 
21
- **model_description**:
22
- The 169Pi/generic_slm is a fine-tuned version of the Meta-Llama-3.1-8B-bnb-4bit model,
23
- designed to deliver high-quality educational content. Leveraging techniques such as
24
- LoRA, PEFT, and RSLoRA, it aims to provide engaging, accurate, and contextually
25
- appropriate educational materials for students and educators.
26
-
27
- **tags**:
28
- - transformers
29
- - llama
30
- - education
31
- - fine-tuning
32
- - LoRA
33
- - PEFT
34
- - RSLoRA
35
- - quantized
36
-
37
- **uses**:
38
- direct_use:
39
- - Summarizing chapters or concepts
40
- - Answering curriculum-aligned questions
41
- - Generating practice questions and explanations
42
- - Recommending study materials
43
-
44
- **downstream_use**:
45
- - Interactive learning tools
46
- - Educational chatbots
47
- - Personalized study guides
48
- - Automated assessment materials
49
-
50
- **out_of_scope**:
51
- - Legal or financial decision-making
52
- - Generating non-educational content
53
- - Applications requiring high precision in non-educational contexts
54
-
55
- **training_details**:
56
- dataset: Proprietary dataset by 169Pi
57
-
58
- **preprocessing_steps**:
59
- - Removed duplicates
60
- - Cleaned noisy and irrelevant data
61
- - Normalized text for consistency
62
-
63
- **parameter_size**: 4.65 billion (after quantization to 4-bit)
64
-
65
- **hyperparameters**:
66
- - learning_rate: 5e-5
67
- - lr_scheduler_type: cosine
68
- - batch_size_per_device: 32
69
- - gradient_accumulation_steps: 4
70
- - num_epochs: 3
71
- - fp16: True
72
- - bf16: True
73
- - optimizer: adamw_8bit
74
- - weight_decay: 0.05
75
- - warmup_steps: 1000
76
- - logging_steps: 1000
77
- - evaluation_strategy: steps
78
- - eval_steps: 1000
79
- - save_strategy: steps
80
- - save_steps: 1000
81
-
82
-
83
- **architecture**:
84
- base_model: Meta-Llama-3.1-8B
85
- quantization: 4-bit
86
- techniques:
87
- - LoRA
88
- - PEFT
89
- - RSLoRA
90
-
91
- **bias_risks_and_limitations**:
92
- known_biases: >
93
- Potential biases in educational content sources, including cultural or linguistic preferences.
94
- risks: >
95
- Model may generate incorrect or general responses for ambiguous queries.
96
- recommendations: >
97
- Use cautiously in critical contexts. Regularly evaluate outputs for accuracy and bias.
98
-
99
- **technical_specifications**:
100
- model_architecture: >
101
- Transformer-based architecture with multi-head self-attention, enhanced using LoRA,
102
- PEFT, and RSLoRA. Optimized for educational tasks.
103
-
104
- **objective**: >
105
- Generate high-quality educational content, including summarization, question-answering,
106
- and study material generation.
107
-
108
- **evaluation**:
109
- metrics:
110
- primary: Loss during training
111
- secondary: Accuracy and relevance through manual evaluation
112
-
113
- **results**: >
114
- Achieved low validation loss during training, demonstrating generalization capability.
115
-
116
- **environmental_impact**:
117
- hardware: NVIDIA A100
118
-
119
- **training_duration**: 26 hours
120
-
121
-
122
- **citation**: >
123
- @misc{169Pi_generic_slm,
124
-
125
- title={169Pi/generic_slm: Fine-Tuned Educational Model},
126
-
127
- author={169Pi},
128
-
129
- year={2024},
130
-
131
- publisher={Hugging Face},
132
-
133
- url={https://huggingface.co/169Pi/generic_slm}
134
- }
135
-
136
- **contact**:
137
- developer: 169Pi AI
138
-
139
- email: contact@169pi.com
 
 
 
 
 
 
 
18
  ---
19
  **model_name: 169Pi/generic_slm**
20
 
21
+ ## Model Description
22
+
23
+ The **169Pi/generic_slm** is a fine-tuned version of the Meta-Llama-3.1-8B-bnb-4bit model, designed to deliver high-quality educational content. Leveraging techniques such as LoRA, PEFT, and RSLoRA, it aims to provide engaging, accurate, and contextually appropriate educational materials for students and educators.
24
+
25
+ ## Tags
26
+
27
+ - transformers
28
+ - llama
29
+ - education
30
+ - fine-tuning
31
+ - LoRA
32
+ - PEFT
33
+ - RSLoRA
34
+ - quantized
35
+
36
+ ## Uses
37
+
38
+ ### Direct Use
39
+ - Summarizing chapters or concepts
40
+ - Answering curriculum-aligned questions
41
+ - Generating practice questions and explanations
42
+ - Recommending study materials
43
+
44
+ ### Downstream Use
45
+ - Interactive learning tools
46
+ - Educational chatbots
47
+ - Personalized study guides
48
+ - Automated assessment materials
49
+
50
+ ### Out of Scope
51
+ - Legal or financial decision-making
52
+ - Generating non-educational content
53
+ - Applications requiring high precision in non-educational contexts
54
+
55
+ ## Training Details
56
+
57
+ ### Dataset
58
+ Proprietary dataset by 169Pi
59
+
60
+ ### Preprocessing Steps
61
+ - Removed duplicates
62
+ - Cleaned noisy and irrelevant data
63
+ - Normalized text for consistency
64
+
65
+ ### Parameter Size
66
+ 4.65 billion (quantized to 4-bit)
67
+
68
+ ### Hyperparameters
69
+ - **learning_rate**: 5e-5
70
+ - **lr_scheduler_type**: cosine
71
+ - **batch_size_per_device**: 32
72
+ - **gradient_accumulation_steps**: 4
73
+ - **num_epochs**: 3
74
+ - **fp16**: True
75
+ - **bf16**: True
76
+ - **optimizer**: adamw_8bit
77
+ - **weight_decay**: 0.05
78
+ - **warmup_steps**: 1000
79
+ - **logging_steps**: 1000
80
+ - **evaluation_strategy**: steps
81
+ - **eval_steps**: 1000
82
+ - **save_strategy**: steps
83
+ - **save_steps**: 1000
84
+
85
+ ## Architecture
86
+
87
+ ### Base Model
88
+ Meta-Llama-3.1-8B
89
+
90
+ ### Quantization
91
+ 4-bit
92
+
93
+ ### Techniques
94
+ - LoRA
95
+ - PEFT
96
+ - RSLoRA
97
+
98
+ ## Bias, Risks, and Limitations
99
+
100
+ ### Known Biases
101
+ Potential biases in educational content sources, including cultural or linguistic preferences.
102
+
103
+ ### Risks
104
+ Model may generate incorrect or general responses for ambiguous queries.
105
+
106
+ ### Recommendations
107
+ Use cautiously in critical contexts. Regularly evaluate outputs for accuracy and bias.
108
+
109
+ ## Technical Specifications
110
+
111
+ ### Model Architecture
112
+ Transformer-based architecture with multi-head self-attention, enhanced using LoRA, PEFT, and RSLoRA. Optimized for educational tasks.
113
+
114
+ ### Objective
115
+ Generate high-quality educational content, including summarization, question-answering, and study material generation.
116
+
117
+ ## Evaluation
118
+
119
+ ### Metrics
120
+ - **Primary**: Loss during training
121
+ - **Secondary**: Accuracy and relevance through manual evaluation
122
+
123
+ ### Results
124
+ Achieved low validation loss during training, demonstrating generalization capability.
125
+
126
+ ## Environmental Impact
127
+
128
+ - **Hardware**: NVIDIA A100
129
+ - **Training Duration**: 26 hours
130
+
131
+ ## Citation
132
+
133
+ ```bibtex
134
+ @misc{169Pi_generic_slm,
135
+ title={169Pi/generic_slm: Fine-Tuned Educational Model},
136
+ author={169Pi},
137
+ year={2024},
138
+ publisher={Hugging Face},
139
+ url={https://huggingface.co/169Pi/generic_slm}
140
+ }
141
+
142
+ ## Contact
143
+
144
+ - **Developer**: 169Pi AI
145
+ - **Email**: [[email protected]](mailto:[email protected])