Update README.md
Browse files
README.md
CHANGED
@@ -33,6 +33,7 @@ Nous Hermes 2 SOLAR 10.7B was trained on 1,000,000 entries of primarily GPT-4 ge
|
|
33 |
- AGIEval
|
34 |
- BigBench
|
35 |
- Averages Compared
|
|
|
36 |
2. [Prompt Format](#prompt-format)
|
37 |
3. [Quantized Models](#quantized-models)
|
38 |
|
@@ -40,6 +41,12 @@ Nous Hermes 2 SOLAR 10.7B was trained on 1,000,000 entries of primarily GPT-4 ge
|
|
40 |
|
41 |
Nous-Hermes 2 on SOLAR 10.7B is a major improvement across the board on the benchmarks below compared to the base SOLAR 10.7B model, and comes close to approaching our Yi-34B model!
|
42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
43 |
# Benchmarks Compared
|
44 |
|
45 |
GPT4All:
|
|
|
33 |
- AGIEval
|
34 |
- BigBench
|
35 |
- Averages Compared
|
36 |
+
2. [Example Outputs](#example-outputs)
|
37 |
2. [Prompt Format](#prompt-format)
|
38 |
3. [Quantized Models](#quantized-models)
|
39 |
|
|
|
41 |
|
42 |
Nous-Hermes 2 on SOLAR 10.7B is a major improvement across the board on the benchmarks below compared to the base SOLAR 10.7B model, and comes close to approaching our Yi-34B model!
|
43 |
|
44 |
+
## Example Outputs
|
45 |
+
|
46 |
+
### Ask for help creating a discord bot:
|
47 |
+
|
48 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6317aade83d8d2fd903192d9/jPaRbNms1mHRD-Lxh7B9R.png)
|
49 |
+
|
50 |
# Benchmarks Compared
|
51 |
|
52 |
GPT4All:
|