Update README.md
Browse files
README.md
CHANGED
|
@@ -224,8 +224,8 @@ The model achieved strong performance on code review tasks, particularly excelli
|
|
| 224 |
The model demonstrates excellent capability in identifying and fixing common Python code issues, with particular strength in security vulnerability detection and code quality improvements.
|
| 225 |
|
| 226 |
## Environmental Impact
|
| 227 |
-
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
|
| 228 |
-
- Hardware Type: NVIDIA
|
| 229 |
- Hours used: ~1.5 hours
|
| 230 |
- Training Approach: QLoRA for efficient fine-tuning
|
| 231 |
|
|
@@ -237,7 +237,7 @@ Carbon emissions can be estimated using the Machine Learning Impact calculator p
|
|
| 237 |
|
| 238 |
### Compute Infrastructure
|
| 239 |
**Hardware**
|
| 240 |
-
- Training performed on GPU cluster with NVIDIA
|
| 241 |
|
| 242 |
**Software**
|
| 243 |
- Transformers, PEFT, TRL, BitsAndBytes
|
|
@@ -245,19 +245,19 @@ Carbon emissions can be estimated using the Machine Learning Impact calculator p
|
|
| 245 |
|
| 246 |
## Citation
|
| 247 |
@misc{alen_philip_george_2025,
|
| 248 |
-
|
| 249 |
-
|
| 250 |
-
|
| 251 |
-
|
| 252 |
-
|
| 253 |
-
|
| 254 |
}
|
| 255 |
## Model Card Authors
|
| 256 |
- Alen Philip George
|
| 257 |
|
| 258 |
## Model Card Contact
|
| 259 |
Hugging Face: alenphilip
|
| 260 |
-
LinkedIn: linkedin.com/in/alen-philip-george-130226254
|
| 261 |
Email: alenphilipgeorge@gmail.com
|
| 262 |
|
| 263 |
|
|
|
|
| 224 |
The model demonstrates excellent capability in identifying and fixing common Python code issues, with particular strength in security vulnerability detection and code quality improvements.
|
| 225 |
|
| 226 |
## Environmental Impact
|
| 227 |
+
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).
|
| 228 |
+
- Hardware Type: NVIDIA H100 80GB VRAM
|
| 229 |
- Hours used: ~1.5 hours
|
| 230 |
- Training Approach: QLoRA for efficient fine-tuning
|
| 231 |
|
|
|
|
| 237 |
|
| 238 |
### Compute Infrastructure
|
| 239 |
**Hardware**
|
| 240 |
+
- Training performed on GPU cluster with NVIDIA H100 80GB VRAM
|
| 241 |
|
| 242 |
**Software**
|
| 243 |
- Transformers, PEFT, TRL, BitsAndBytes
|
|
|
|
| 245 |
|
| 246 |
## Citation
|
| 247 |
@misc{alen_philip_george_2025,
|
| 248 |
+
author = {Alen Philip George},
|
| 249 |
+
title = {Code_Review_Assistant_Model (Revision 233d438)},
|
| 250 |
+
year = 2025,
|
| 251 |
+
url = {https://huggingface.co/alenphilip/Code_Review_Assistant_Model},
|
| 252 |
+
doi = {10.57967/hf/6836},
|
| 253 |
+
publisher = {Hugging Face}
|
| 254 |
}
|
| 255 |
## Model Card Authors
|
| 256 |
- Alen Philip George
|
| 257 |
|
| 258 |
## Model Card Contact
|
| 259 |
Hugging Face: alenphilip
|
| 260 |
+
LinkedIn: [alenphilipgeorge](linkedin.com/in/alen-philip-george-130226254)
|
| 261 |
Email: alenphilipgeorge@gmail.com
|
| 262 |
|
| 263 |
|