Commit ·
c9e9ae7
1
Parent(s): 57135e7
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,9 +35,7 @@ Here are the results on metrics used by [HuggingFaceH4 Open LLM Leaderboard](htt
|
|
| 35 |
|**Total Average**|**0.6503**|
|
| 36 |
|
| 37 |
|
| 38 |
-
##
|
| 39 |
-
|
| 40 |
-
Here is the prompt format
|
| 41 |
|
| 42 |
```
|
| 43 |
### System:
|
|
@@ -50,6 +48,23 @@ Tell me about Orcas.
|
|
| 50 |
|
| 51 |
```
|
| 52 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
Below shows a code example on how to use this model
|
| 54 |
|
| 55 |
```python
|
|
|
|
| 35 |
|**Total Average**|**0.6503**|
|
| 36 |
|
| 37 |
|
| 38 |
+
### Prompt Format
|
|
|
|
|
|
|
| 39 |
|
| 40 |
```
|
| 41 |
### System:
|
|
|
|
| 48 |
|
| 49 |
```
|
| 50 |
|
| 51 |
+
#### OobaBooga Instructions:
|
| 52 |
+
|
| 53 |
+
This model required upto 45GB GPU VRAM in 4bit so it can be loaded directly on Single RTX 6000/L40/A40/A100/H100 GPU or Double RTX 4090/L4/A10/RTX 3090/RTX A5000
|
| 54 |
+
So, if you have access to Machine with 45GB GPU VRAM and have installed [OobaBooga Web UI](https://github.com/oobabooga/text-generation-webui) on it.
|
| 55 |
+
You can just download this model by using HF repo link directly on OobaBooga Web UI "Model" Tab/Page & Just use **load-in-4bit** option in it.
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
After that go to Default Tab/Page on OobaBooga Web UI and **copy paste above prompt format into Input** and Enjoy!
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
<br>
|
| 65 |
+
|
| 66 |
+
#### Code Instructions:
|
| 67 |
+
|
| 68 |
Below shows a code example on how to use this model
|
| 69 |
|
| 70 |
```python
|