eval
Browse files
README.md
CHANGED
|
@@ -14,4 +14,14 @@ license: llama2
|
|
| 14 |
|
| 15 |
Stellar Bright is a general capability upgrade to Llama 2, using open source data to improve overall knowledge, extended communication, and technical skill.
|
| 16 |
|
| 17 |
-
This model is primarily recommended as a superior-to-Llama-2 baseline for additional finetuning, **not** for direct deployment to production as a chat model. The user accepts full responsibility for all outputs.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
|
| 15 |
Stellar Bright is a general capability upgrade to Llama 2, using open source data to improve overall knowledge, extended communication, and technical skill.
|
| 16 |
|
| 17 |
+
This model is primarily recommended as a superior-to-Llama-2 baseline for additional finetuning, **not** for direct deployment to production as a chat model. The user accepts full responsibility for all outputs.
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
## Evaluation
|
| 22 |
+
|
| 23 |
+
| Model | Avg | ARC | HS | MMLU | TQA |
|
| 24 |
+
|-----------------------|--------|-------|-------|--------|-------|
|
| 25 |
+
| **Stellar Bright** | 74.10 | 72.95 | 87.82 | 71.17 | 64.46 |
|
| 26 |
+
| Llama 2 | 67.35 | 67.32 | 87.33 | 69.83 | 44.92 |
|
| 27 |
+
| Llama 2 Chat | 66.80 | 64.59 | 85.88 | 63.91 | 52.80 |
|