Commit
•
5098851
1
Parent(s):
d5f6c8b
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ tags:
|
|
| 11 |
|
| 12 |
## TeTO-MS-8x7b
|
| 13 |
|
| 14 |
-
<b>Te</b>soro + <b>T</b>yphon + <b>O</b>penGPT
|
| 15 |
|
| 16 |
Presenting a Model Stock experiment combining the unique strengths from the following 8x7b Mixtral models:
|
| 17 |
* Tess-2.0-Mixtral-8x7B-v0.2 / [migtissera](https://huggingface.co/migtissera) / General Purpose
|
|
@@ -63,7 +63,7 @@ dtype: float16
|
|
| 63 |
|
| 64 |
## Apendix - Llama.cpp MMLU Benchmark Results*
|
| 65 |
|
| 66 |
-
<i>These results were calculated
|
| 67 |
|
| 68 |
`.\perplexity -m .\models\TeTO-8x7b-MS-v0.03\TeTO-MS-8x7b-Q6_K.gguf -bf .\evaluations\mmlu-test.bin --multiple-choice -c 8192 -t 23 -ngl 200`
|
| 69 |
|
|
|
|
| 11 |
|
| 12 |
## TeTO-MS-8x7b
|
| 13 |
|
| 14 |
+
<u><b>Te</b></u>soro + <u><b>T</b></u>yphon + <u><b>O</b></u>penGPT
|
| 15 |
|
| 16 |
Presenting a Model Stock experiment combining the unique strengths from the following 8x7b Mixtral models:
|
| 17 |
* Tess-2.0-Mixtral-8x7B-v0.2 / [migtissera](https://huggingface.co/migtissera) / General Purpose
|
|
|
|
| 63 |
|
| 64 |
## Apendix - Llama.cpp MMLU Benchmark Results*
|
| 65 |
|
| 66 |
+
<i>These results were calculated via perplexity.exe from llama.cpp using the following params:</i>
|
| 67 |
|
| 68 |
`.\perplexity -m .\models\TeTO-8x7b-MS-v0.03\TeTO-MS-8x7b-Q6_K.gguf -bf .\evaluations\mmlu-test.bin --multiple-choice -c 8192 -t 23 -ngl 200`
|
| 69 |
|