https://github.com/maxpaynestory/llama2-llm-generative-ai-nlp-resume-writer

This is a Generative AI bot fine tuned to become a Professional resume writer. It used Meta's LlaMA 2 LLM with langchain. System Prompt has been changed in order to change profile of AI.
https://github.com/maxpaynestory/llama2-llm-generative-ai-nlp-resume-writer

huggingface langchain llm nlp-machine-learning prompt-engineering prompt-tuning python

Last synced: about 1 month ago
JSON representation

This is a Generative AI bot fine tuned to become a Professional resume writer. It used Meta's LlaMA 2 LLM with langchain. System Prompt has been changed in order to change profile of AI.

• Host: GitHub
• URL: https://github.com/maxpaynestory/llama2-llm-generative-ai-nlp-resume-writer
• Owner: maxpaynestory
• Created: 2023-10-30T16:32:38.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2024-01-06T07:41:34.000Z (over 1 year ago)
• Last Synced: 2025-04-02T09:22:23.392Z (about 2 months ago)
• Topics: huggingface, langchain, llm, nlp-machine-learning, prompt-engineering, prompt-tuning, python
• Language: HTML
• Homepage:
• Size: 161 KB
• Stars: 10
• Watchers: 1
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
**In the name of ALLAH, who has guided me to do this work**

# LlaMA 2 7B LLM Generative AI NLP Professional resume writer

This tool will help you to get a job interview by simply aligning your resume with the job Ad requirements. This tool uses Meta's famous Llama 2 large language model.

![Add resume and the job](/screens/writer-form.PNG "Add resume and the job")

![AI is generating resume](/screens/aliging-resume.PNG "AI is generating resume")

![New resume](/screens/generated-resume.PNG "New resume")

## Run Locally

### 1. Download LlaMA 2 model from Hugging Face

[LlaMA 2 7b Model GGUF file](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/resolve/main/llama-2-7b-chat.Q8_0.gguf) 7 GB

### 2. Place downloaded file path inside llama_cpu.py

```python

MODEL_PATH = "D:\\path\\to\\folder\\llama-2-7b-chat.Q8_0.gguf"

```

### 3. Install Packages Python version is 3.9.18

```sh

$ pip install -r requirements.txt

```

### 4. Run server

```sh

$ uvicorn api:app

```

### 5. Open frontend

Open browser and navigate to URL

http://127.0.0.1:8000/frontend/index.html

## CPU/RAM requirements

Atleast a good 6 core CPU.

12 GB of free RAM.