Update README.md
Browse files
README.md
CHANGED
@@ -25,9 +25,11 @@ This metaphorically represents the model's depth, fluidity, and adaptability in
|
|
25 |
It also perfectly fits the approach taken here - Depth Upscaling, inspired by SOLAR 10.7B.
|
26 |
|
27 |
## Nous LLM Evaluation (with ChatML Prompt Template)
|
28 |
-
|
|
29 |
-
|
30 |
-
|
|
|
|
|
|
31 |
|
32 |
More details can be found [here](https://gist.github.com/sethuiyer/08b4498ed13a6dead38ad3a6f12e349a)
|
33 |
|
|
|
25 |
It also perfectly fits the approach taken here - Depth Upscaling, inspired by SOLAR 10.7B.
|
26 |
|
27 |
## Nous LLM Evaluation (with ChatML Prompt Template)
|
28 |
+
| Model | AGIEval | GPT4All | TruthfulQA | Bigbench | Average |
|
29 |
+
|---------------------------|---------|----------|------------|-----------|---------|
|
30 |
+
| SynthIQ-7b | 42.67 | **73.71** | 56.51 | **44.59** | **54.37** |
|
31 |
+
| openchat/openchat-3.5-0106 | **44.17** | 73.72 | 52.53 | 44.4 | 53.71 |
|
32 |
+
| Chikuma_10.7B | 42.41 | 73.41 | **56.69** | 43.5 | 54 |
|
33 |
|
34 |
More details can be found [here](https://gist.github.com/sethuiyer/08b4498ed13a6dead38ad3a6f12e349a)
|
35 |
|