Update README.md
Browse files
README.md
CHANGED
|
@@ -35,13 +35,13 @@ This is a fine-tuned version of the **Gemma-2-2B-IT** model, aimed at helping us
|
|
| 35 |
<!-- - **License:** [More Information Needed] -->
|
| 36 |
- **Finetuned from model [optional]:** [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it)
|
| 37 |
|
| 38 |
-
### Model Sources
|
| 39 |
|
| 40 |
<!-- Provide the basic links for the model. -->
|
| 41 |
|
| 42 |
- **Repository:** [gemma-2-2b-it-ThinkLink](https://huggingface.co/MinnieMin/gemma-2-2b-it-ThinkLink)
|
| 43 |
-
- **Paper [optional]:** [More Information Needed]
|
| 44 |
-
- **Demo [optional]:** [More Information Needed]
|
| 45 |
|
| 46 |
## Uses
|
| 47 |
|
|
@@ -54,7 +54,7 @@ This is a fine-tuned version of the **Gemma-2-2B-IT** model, aimed at helping us
|
|
| 54 |
This model can be used for educational purposes, especially for coding test preparation. It generates step-by-step problem-solving hints and structured questions to guide users through coding problems.
|
| 55 |
|
| 56 |
|
| 57 |
-
### Downstream Use
|
| 58 |
|
| 59 |
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 60 |
|
|
@@ -68,11 +68,11 @@ This model can be used for educational purposes, especially for coding test prep
|
|
| 68 |
- Direct code generation without understanding the steps may lead to incorrect or misleading results.
|
| 69 |
- It is not suitable for tasks that require a detailed and immediate answer to general-purpose questions or advanced mathematical computations.
|
| 70 |
|
| 71 |
-
## Bias, Risks, and Limitations
|
| 72 |
|
| 73 |
-
|
| 74 |
|
| 75 |
-
[More Information Needed]
|
| 76 |
|
| 77 |
### Recommendations
|
| 78 |
|
|
@@ -115,87 +115,47 @@ The model was fine-tuned on a dataset of structured coding test problems and sol
|
|
| 115 |
- Fine-tuning approach: Low-Rank Adaptation (LoRA)
|
| 116 |
|
| 117 |
|
| 118 |
-
#### Training Hyperparameters
|
| 119 |
-
|
| 120 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 121 |
|
| 122 |
#### Speeds, Sizes, Times [optional]
|
| 123 |
|
| 124 |
-
|
| 125 |
|
| 126 |
[More Information Needed]
|
| 127 |
|
| 128 |
## Evaluation
|
| 129 |
|
| 130 |
-
|
| 131 |
|
| 132 |
### Testing Data, Factors & Metrics
|
| 133 |
|
| 134 |
#### Testing Data
|
| 135 |
|
| 136 |
-
|
| 137 |
|
| 138 |
[More Information Needed]
|
| 139 |
|
| 140 |
#### Factors
|
| 141 |
|
| 142 |
-
|
| 143 |
|
| 144 |
[More Information Needed]
|
| 145 |
|
| 146 |
#### Metrics
|
| 147 |
|
| 148 |
-
|
| 149 |
-
|
| 150 |
|
| 151 |
[More Information Needed]
|
| 152 |
|
| 153 |
### Results
|
| 154 |
|
| 155 |
-
[More Information Needed]
|
| 156 |
|
| 157 |
#### Summary
|
| 158 |
The model was able to effectively guide users through various coding challenges by providing structured hints and questions that promoted deeper understanding.
|
| 159 |
|
| 160 |
|
| 161 |
-
|
| 162 |
-
## Model Examination [optional]
|
| 163 |
-
|
| 164 |
-
<!-- Relevant interpretability work for the model goes here -->
|
| 165 |
-
|
| 166 |
-
[More Information Needed]
|
| 167 |
-
|
| 168 |
-
## Environmental Impact
|
| 169 |
-
|
| 170 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 171 |
-
|
| 172 |
-
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).
|
| 173 |
-
|
| 174 |
-
- **Hardware Type:** [More Information Needed]
|
| 175 |
-
- **Hours used:** [More Information Needed]
|
| 176 |
-
- **Cloud Provider:** [More Information Needed]
|
| 177 |
-
- **Compute Region:** [More Information Needed]
|
| 178 |
-
- **Carbon Emitted:** [More Information Needed]
|
| 179 |
-
|
| 180 |
-
## Technical Specifications [optional]
|
| 181 |
-
|
| 182 |
-
### Model Architecture and Objective
|
| 183 |
-
|
| 184 |
-
[More Information Needed]
|
| 185 |
-
|
| 186 |
-
### Compute Infrastructure
|
| 187 |
-
|
| 188 |
-
[More Information Needed]
|
| 189 |
-
|
| 190 |
-
#### Hardware
|
| 191 |
-
|
| 192 |
-
[More Information Needed]
|
| 193 |
-
|
| 194 |
-
#### Software
|
| 195 |
-
|
| 196 |
-
[More Information Needed]
|
| 197 |
-
|
| 198 |
-
## Citation [optional]
|
| 199 |
|
| 200 |
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 201 |
|
|
@@ -206,26 +166,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
| 206 |
title = {ThinkLink Gemma-2-2B-IT: A Guided Problem-Solving Model},
|
| 207 |
year = {2024},
|
| 208 |
url = {https://huggingface.co/MinnieMin/gemma-2-2b-it-ThinkLink},
|
| 209 |
-
}
|
| 210 |
-
|
| 211 |
-
**APA:**
|
| 212 |
-
|
| 213 |
-
[More Information Needed]
|
| 214 |
-
|
| 215 |
-
## Glossary [optional]
|
| 216 |
-
|
| 217 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 218 |
-
|
| 219 |
-
[More Information Needed]
|
| 220 |
-
|
| 221 |
-
## More Information [optional]
|
| 222 |
-
|
| 223 |
-
[More Information Needed]
|
| 224 |
-
|
| 225 |
-
## Model Card Authors [optional]
|
| 226 |
-
|
| 227 |
-
[More Information Needed]
|
| 228 |
-
|
| 229 |
-
## Model Card Contact
|
| 230 |
-
|
| 231 |
-
[More Information Needed]
|
|
|
|
| 35 |
<!-- - **License:** [More Information Needed] -->
|
| 36 |
- **Finetuned from model [optional]:** [google/gemma-2-2b-it](https://huggingface.co/google/gemma-2-2b-it)
|
| 37 |
|
| 38 |
+
### Model Sources
|
| 39 |
|
| 40 |
<!-- Provide the basic links for the model. -->
|
| 41 |
|
| 42 |
- **Repository:** [gemma-2-2b-it-ThinkLink](https://huggingface.co/MinnieMin/gemma-2-2b-it-ThinkLink)
|
| 43 |
+
<!-- - **Paper [optional]:** [More Information Needed]
|
| 44 |
+
- **Demo [optional]:** [More Information Needed] -->
|
| 45 |
|
| 46 |
## Uses
|
| 47 |
|
|
|
|
| 54 |
This model can be used for educational purposes, especially for coding test preparation. It generates step-by-step problem-solving hints and structured questions to guide users through coding problems.
|
| 55 |
|
| 56 |
|
| 57 |
+
### Downstream Use
|
| 58 |
|
| 59 |
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 60 |
|
|
|
|
| 68 |
- Direct code generation without understanding the steps may lead to incorrect or misleading results.
|
| 69 |
- It is not suitable for tasks that require a detailed and immediate answer to general-purpose questions or advanced mathematical computations.
|
| 70 |
|
| 71 |
+
<!-- ## Bias, Risks, and Limitations
|
| 72 |
|
| 73 |
+
This section is meant to convey both technical and sociotechnical limitations.
|
| 74 |
|
| 75 |
+
[More Information Needed] -->
|
| 76 |
|
| 77 |
### Recommendations
|
| 78 |
|
|
|
|
| 115 |
- Fine-tuning approach: Low-Rank Adaptation (LoRA)
|
| 116 |
|
| 117 |
|
| 118 |
+
<!-- #### Training Hyperparameters
|
|
|
|
|
|
|
| 119 |
|
| 120 |
#### Speeds, Sizes, Times [optional]
|
| 121 |
|
| 122 |
+
This section provides information about throughput, start/end time, checkpoint size if relevant, etc.
|
| 123 |
|
| 124 |
[More Information Needed]
|
| 125 |
|
| 126 |
## Evaluation
|
| 127 |
|
| 128 |
+
This section describes the evaluation protocols and provides the results.
|
| 129 |
|
| 130 |
### Testing Data, Factors & Metrics
|
| 131 |
|
| 132 |
#### Testing Data
|
| 133 |
|
| 134 |
+
This should link to a Dataset Card if possible.
|
| 135 |
|
| 136 |
[More Information Needed]
|
| 137 |
|
| 138 |
#### Factors
|
| 139 |
|
| 140 |
+
These are the things the evaluation is disaggregating by, e.g., subpopulations or domains.
|
| 141 |
|
| 142 |
[More Information Needed]
|
| 143 |
|
| 144 |
#### Metrics
|
| 145 |
|
| 146 |
+
These are the evaluation metrics being used, ideally with a description of why.
|
|
|
|
| 147 |
|
| 148 |
[More Information Needed]
|
| 149 |
|
| 150 |
### Results
|
| 151 |
|
| 152 |
+
[More Information Needed] -->
|
| 153 |
|
| 154 |
#### Summary
|
| 155 |
The model was able to effectively guide users through various coding challenges by providing structured hints and questions that promoted deeper understanding.
|
| 156 |
|
| 157 |
|
| 158 |
+
## Citation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 159 |
|
| 160 |
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 161 |
|
|
|
|
| 166 |
title = {ThinkLink Gemma-2-2B-IT: A Guided Problem-Solving Model},
|
| 167 |
year = {2024},
|
| 168 |
url = {https://huggingface.co/MinnieMin/gemma-2-2b-it-ThinkLink},
|
| 169 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|