ajibawa-2023
commited on
Commit
•
f4285a4
1
Parent(s):
962080b
Update README.md
Browse files
README.md
CHANGED
@@ -14,4 +14,52 @@ tags:
|
|
14 |
|
15 |
**OpenHermes-2.5-Code-290k-13B**
|
16 |
|
17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
14 |
|
15 |
**OpenHermes-2.5-Code-290k-13B**
|
16 |
|
17 |
+
OpenHermes-2.5-Code-290k-13B is a state of the art Llama-2 Fine-tune, which is trained on additional code dataset.
|
18 |
+
This model is trained on my existing dataset [OpenHermes-2.5-Code-290k](https://huggingface.co/datasets/ajibawa-2023/OpenHermes-2.5-Code-290k).
|
19 |
+
This dataset is amalgamation of two datasets. I have used [OpenHermes-2.5](https://huggingface.co/datasets/teknium/OpenHermes-2.5) a super quality dataset made avaliable by teknium. Other datset is my own [Code-290k-ShareGPT](https://huggingface.co/datasets/ajibawa-2023/Code-290k-ShareGPT).
|
20 |
+
Dataset is in Vicuna/ShareGPT format. There are around 1.29 million set of conversations. I have cleaned the dataset provided by Teknium and removed metadata such as "source" & "category" etc. This dataset has primarily synthetically generated instruction and chat samples.
|
21 |
+
|
22 |
+
This model has enhanced coding capabilities besides other capabilities such as **Blogging, story generation, Q&A and many more**.
|
23 |
+
|
24 |
+
**Training:**
|
25 |
+
|
26 |
+
Entire model was trained on 4 x A100 80GB. For 2 epoch, training took **21 Days**. Fschat & DeepSpeed codebase was used for training purpose. This was trained on Llama-2 by Meta.
|
27 |
+
|
28 |
+
|
29 |
+
This is a full fine tuned model. Links for quantized models will updated soon.
|
30 |
+
|
31 |
+
|
32 |
+
**GPTQ, GGUF, AWQ & Exllama**
|
33 |
+
|
34 |
+
GPTQ: TBA
|
35 |
+
|
36 |
+
GGUF: TBA
|
37 |
+
|
38 |
+
AWQ: TBA
|
39 |
+
|
40 |
+
Exllama v2: TBA
|
41 |
+
|
42 |
+
|
43 |
+
|
44 |
+
|
45 |
+
|
46 |
+
**Example Prompt:**
|
47 |
+
```
|
48 |
+
This is a conversation with your helpful AI assistant. AI assistant can generate Code in various Programming Languages along with necessary explanation. It can generate Story, Blogs .....
|
49 |
+
|
50 |
+
Context
|
51 |
+
You are a helpful AI assistant.
|
52 |
+
|
53 |
+
USER: <prompt>
|
54 |
+
ASSISTANT:
|
55 |
+
```
|
56 |
+
|
57 |
+
You can modify above Prompt as per your requirement. I have used ShareGPT/Vicuna format v1.1 .
|
58 |
+
|
59 |
+
I want to say special Thanks to the Open Source community for helping & guiding me to better understand the AI/Model development.
|
60 |
+
|
61 |
+
Thank you for your love & support.
|
62 |
+
|
63 |
+
**Example Output**
|
64 |
+
|
65 |
+
I will update soon.
|