File size: 2,137 Bytes
5125cee
 
 
 
 
 
 
 
 
c971583
 
 
 
 
 
 
 
 
 
 
 
a5f399f
c971583
5125cee
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3c7df6c
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
# Topic Prompt Generator

If you've ever struggled to find the perfect prompt for your use case, look no further. My new model is designed to generate accurate and efficient prompts for any given topic. 💡✨

This project utilizes the `mistral-7b-v0.3-bnb-4bit` model and the `fka/awesome-chatgpt-prompts` dataset to generate topic prompts efficiently. I also fine-tuned it using Unsloath AI for even better performance.


I'd love to hear your feedback! Feel free to share your thoughts and experiences. Your feedbacks are invaluable. 🙌

## Example
we will try to generate a prompt for **Product Owner and Product Manager** topic.

```plaintext
### Instruction:
As a skilled prompt engineer, your task is to generate an effective prompt using the given keywords mentioned in the '### Input' section. Ensure the prompt is clear, concise, and designed to elicit a detailed and relevant response.

### Input:
Product Owner and Product Manager

### Response:
I want you to act as a product owner and product manager for a new software project. You will be responsible for defining the product vision, creating user stories, prioritizing features, managing the product backlog, and collaborating with the development team to ensure the success of the project. My first suggestion request is "I need help creating a new mobile app for managing personal finances."
```

## Model Details

- **Base Model:** `unsloth/mistral-7b-v0.3-bnb-4bit`
- **Language:** English
- **License:** Apache-2.0
- **Tags:** text-generation-inference, transformers, unsloth, mistral, trl
- **Datasets:** `fka/awesome-chatgpt-prompts`
- **Pipeline Tag:** text-generation

## Uploaded Model Information

- **Developed by:** [Hassen Amri](https://www.linkedin.com/in/hassenamri005/)
- **License:** Apache-2.0
- **Finetuned from Model:** `unsloth/mistral-7b-v0.3-bnb-4bit`

This Mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Hugging Face's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)