Update README.md
Browse files
README.md
CHANGED
|
@@ -52,6 +52,8 @@ The ethos of the Hermes series of models is focused on aligning LLMs to the user
|
|
| 52 |
|
| 53 |
|
| 54 |
|
|
|
|
|
|
|
| 55 |
## Benchmarks in **Non-Reasoning Mode** against Llama-3.1-8B-Instruct
|
| 56 |
|
| 57 |
|
|
|
|
| 52 |
|
| 53 |
|
| 54 |
|
| 55 |
+
*Upper bound determined by measuring the % gained over Hermes 3 3 & 70b by MATH_VERIFY compared to eleuther eval harness, which ranged betweeen 33% and 50% gain in MATH Hard benchmark on retested models by them compared to eval harness reported scores*
|
| 56 |
+
|
| 57 |
## Benchmarks in **Non-Reasoning Mode** against Llama-3.1-8B-Instruct
|
| 58 |
|
| 59 |
|