Commit
·
ad623db
1
Parent(s):
c3f82fd
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,70 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-nd-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-nd-4.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- code
|
| 7 |
---
|
| 8 |
+
|
| 9 |
+
**Code-13B**
|
| 10 |
+
|
| 11 |
+
Large Language Models (LLMs) are good with code generations. Sometimes they do make mistakes in code generation. How about if they can give detailed explanation along with the code.
|
| 12 |
+
This is what I have tried over here. The base Llama-2 model was used for training purpose. It is trained on around 74000 set of codes. Each set having 2 conversations.
|
| 13 |
+
Along with Python, Java, JavaScript, GO, C++, Rust etc. code with detailed explanation is used for training purpose. It is built upon using my existing Dataset [Python-Code-23k-ShareGPT](https://huggingface.co/datasets/ajibawa-2023/Python-Code-23k-ShareGPT).
|
| 14 |
+
This conversation is in Vicuna/ShareGPT format. Each set, along with code, has detailed explanation.
|
| 15 |
+
I have released the new [data](https://huggingface.co/datasets/ajibawa-2023/Python-Code-23k-ShareGPT).
|
| 16 |
+
|
| 17 |
+
**Training:**
|
| 18 |
+
|
| 19 |
+
Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 42 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.
|
| 20 |
+
|
| 21 |
+
This is a full fine tuned model. Links for quantized models will be released soon.
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
**GPTQ GGUF & AWQ**
|
| 25 |
+
|
| 26 |
+
GPTQ: TBA
|
| 27 |
+
|
| 28 |
+
GGUF: TBA
|
| 29 |
+
|
| 30 |
+
AWQ: TBA
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
**Example Prompt:**
|
| 34 |
+
```
|
| 35 |
+
This is a conversation with your helpful AI assistant. AI assistant can generate Code in various Programming Languages along with necessary explanation.
|
| 36 |
+
|
| 37 |
+
Context
|
| 38 |
+
You are a helpful AI assistant.
|
| 39 |
+
|
| 40 |
+
USER: <prompt>
|
| 41 |
+
ASSISTANT:
|
| 42 |
+
```
|
| 43 |
+
|
| 44 |
+
You can modify above Prompt as per your requirement. I have used ShareGPT/Vicuna format v1.1 .
|
| 45 |
+
|
| 46 |
+
I want to say special Thanks to the Open Source community for helping & guiding me to better understand the AI/Model development.
|
| 47 |
+
|
| 48 |
+
Thank you for your love & support.
|
| 49 |
+
|
| 50 |
+
**Example Output**
|
| 51 |
+
|
| 52 |
+
1. Navier-Stokes Equation Solver
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
|
| 58 |
+
2. KSC Complexity
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
3. GO
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
|