Update README.md
Browse files
README.md
CHANGED
@@ -29,7 +29,7 @@ This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
|
|
29 |
|
30 |
## Model description
|
31 |
|
32 |
-
|
33 |
|
34 |
|
35 |
## Metrics
|
@@ -42,3 +42,6 @@ Coming soon...
|
|
42 |
| Bipolar | 0.71 | 248/351 | 0.75 | 264/351 |
|
43 |
| Anxiety | 0.67 | 277/413 | 0.73 | 303/413 |
|
44 |
| Expressing | 0.64 | 229/359 | 0.77 | 275/359 |
|
|
|
|
|
|
|
|
29 |
|
30 |
## Model description
|
31 |
|
32 |
+
This Large Language Model (LLM), based on **DeepSeek R1 Distill Qwen with 1.5 billion parameters**, is fine-tuned on a dataset of **48,000 records** to classify five distinct mental health-related classes: depression, suicide, bipolar, anxiety, and expressing. The model leverages lightweight quantization techniques (4-bit) for efficient computation while maintaining accuracy. Though designed for experimental and research purposes, it demonstrates the potential to assist in identifying mental health patterns through text, offering valuable insights for educational and academic applications.
|
33 |
|
34 |
|
35 |
## Metrics
|
|
|
42 |
| Bipolar | 0.71 | 248/351 | 0.75 | 264/351 |
|
43 |
| Anxiety | 0.67 | 277/413 | 0.73 | 303/413 |
|
44 |
| Expressing | 0.64 | 229/359 | 0.77 | 275/359 |
|
45 |
+
|
46 |
+
For more information about the usage and metrics you can check this [Kaggle notebook](https://www.kaggle.com/code/sajjadhadi/mental-disorder-detection-test-deepseek-r1-1-5b).
|
47 |
+
|