Commit
•
9e4bcc8
1
Parent(s):
e5d88f9
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,80 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
**SlimOrca-Llama-3-8B: A General Purpose Intelligent Model**
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
This Model is trained on refined version of SlimOrca made available by [Open-Orca](https://huggingface.co/Open-Orca) team.
|
| 9 |
+
This Model is very good in various types of General Purpose content generation such as **Q&A (including multiple choice), Articles from Summary, Sentiment Analysis,
|
| 10 |
+
Context & Hypothesis, Reviews, Erotic story generation** etc.
|
| 11 |
+
To a certain extent it can also generate Uncensored content. Kindly be careful while generating Uncensored content as you will be responsible for what you
|
| 12 |
+
generate.
|
| 13 |
+
|
| 14 |
+
It is trained on 517981 set of conversations. Each set having 2 conversations. I have shared this [data](https://huggingface.co/datasets/ajibawa-2023/SlimOrca-ShareGPT).
|
| 15 |
+
|
| 16 |
+
I have used ChatML prompt format.
|
| 17 |
+
|
| 18 |
+
All the credit goes to the Open-Orca team for releasing SlimOrca dataset.
|
| 19 |
+
|
| 20 |
+
Check examples given below.
|
| 21 |
+
|
| 22 |
+
**Training:**
|
| 23 |
+
Entire dataset was trained on 4 x A100 80GB. For 2 epoch, training took almost 114 hours. Axolotl & DeepSpeed codebase was used for training purpose.
|
| 24 |
+
Entire data is trained on Llama-3 by Meta.
|
| 25 |
+
|
| 26 |
+
This is a fully fine tuned model. Links for quantized models are given below.
|
| 27 |
+
|
| 28 |
+
**GGUF & Exllama**
|
| 29 |
+
|
| 30 |
+
GGUF: TBA
|
| 31 |
+
|
| 32 |
+
Exllama: TBA
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
**Example Prompt:**
|
| 37 |
+
|
| 38 |
+
This model uses **ChatML** prompt format.
|
| 39 |
+
|
| 40 |
+
```
|
| 41 |
+
<|im_start|>system
|
| 42 |
+
You are a helpful Assistant.<|im_end|>
|
| 43 |
+
<|im_start|>user
|
| 44 |
+
{prompt}<|im_end|>
|
| 45 |
+
<|im_start|>assistant
|
| 46 |
+
|
| 47 |
+
```
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
You can modify above Prompt as per your requirement.
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
I want to say special Thanks to the Open Source community for helping & guiding me to better understand the AI/Model development.
|
| 54 |
+
|
| 55 |
+
Thank you for your love & support.
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
**Examples**
|
| 59 |
+
|
| 60 |
+
Example 1
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
Example 2
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
Example 3
|
| 72 |
+
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
Example 4
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
|