Update README.md
Browse files
README.md
CHANGED
|
@@ -8,6 +8,16 @@ tags:
|
|
| 8 |
---
|
| 9 |
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
This model was created with the help of several members of Anthracite.
|
| 12 |
|
| 13 |
This is a 4B parameter Minitron derivative. This model is a slerp merge of NeuroCom v2 and Zenith. This model was tuned at 8k context during all steps. This model should perform well as a general assistant and RP model.
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
|
| 11 |
+
```
|
| 12 |
+
| Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
|
| 13 |
+
|------------------|------:|------|------|------|---|-----:|---|-----:|
|
| 14 |
+
|mmlu | 2|none | |acc |_ |0.5862|_ |0.0039|
|
| 15 |
+
| - humanities | 2|none | |acc |_ |0.5443|_ |0.0068|
|
| 16 |
+
| - other | 2|none | |acc |_ |0.6534|_ |0.0082|
|
| 17 |
+
| - social sciences| 2|none | |acc |_ |0.6766|_ |0.0082|
|
| 18 |
+
| - stem | 2|none | |acc |_ |0.4944|_ |0.0086|
|
| 19 |
+
```
|
| 20 |
+
|
| 21 |
This model was created with the help of several members of Anthracite.
|
| 22 |
|
| 23 |
This is a 4B parameter Minitron derivative. This model is a slerp merge of NeuroCom v2 and Zenith. This model was tuned at 8k context during all steps. This model should perform well as a general assistant and RP model.
|