Update README.md
Browse files
README.md
CHANGED
|
@@ -52,6 +52,18 @@ Evaluated on **ClimaBench**, a benchmark for climate-focused NLP tasks:
|
|
| 52 |
|
| 53 |
Note: While CliSciBERT builds on SciBERT’s scientific grounding, its domain specialization improves relevance for climate-related NLP tasks.
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
## 🧪 Intended Uses
|
| 56 |
|
| 57 |
**Use for:**
|
|
|
|
| 52 |
|
| 53 |
Note: While CliSciBERT builds on SciBERT’s scientific grounding, its domain specialization improves relevance for climate-related NLP tasks.
|
| 54 |
|
| 55 |
+
Climate performance model card:
|
| 56 |
+
|CliSciBERT||
|
| 57 |
+
|---------------------------------|-----------------------------|
|
| 58 |
+
| 1. Model publicly available? | Yes |
|
| 59 |
+
| 2. Time to train final model | 463h |
|
| 60 |
+
| 3. Time for all experiments | 1,226h $\sim$ 51 days |
|
| 61 |
+
| 4. Power of GPU and CPU | 0.250 kW + 0.013 kW |
|
| 62 |
+
| 5. Location for computations | Croatia |
|
| 63 |
+
| 6. Energy mix at location | 224.71 gCO$_2$eq/kWh |
|
| 64 |
+
| 7. CO$_2$eq for final model | 28 kg CO$_2$ (18 kg CO$_2$) |
|
| 65 |
+
| 8. CO$_2$eq for all experiments | 74 kg CO$_2$ |
|
| 66 |
+
|
| 67 |
## 🧪 Intended Uses
|
| 68 |
|
| 69 |
**Use for:**
|