|
|
--- |
|
|
base_model: unsloth/Llama-3.2-3B-Instruct |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- llama |
|
|
- gguf |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
--- |
|
|
# Llama-3.2B Finetuned Model |
|
|
|
|
|
## 1. Introduction |
|
|
This model is a finetuned version of the Llama-3.2B large language model. It has been specifically trained to provide detailed and accurate responses for university course-related queries. This model offers insights on course details, fee structures, duration, and campus options, along with links to corresponding course pages. The finetuning process ensured domain-specific accuracy by utilizing a tailored dataset. |
|
|
|
|
|
--- |
|
|
|
|
|
## GGUF Model: |
|
|
This is a GGUF model made for running offline with Ollama. A Modelfile is also created to locally host and run this model with Ollama |
|
|
|
|
|
## 2. Dataset Used for Finetuning |
|
|
The finetuning of the Llama-3.2B model was performed using a private dataset obtained through web scraping. Data was collected from the University of Westminster website and included: |
|
|
|
|
|
- Course titles |
|
|
- Campus details |
|
|
- Duration options (full-time, part-time, distance learning) |
|
|
- Fee structures (for UK and international students) |
|
|
- Course descriptions |
|
|
- Direct links to course pages |
|
|
|
|
|
This dataset was carefully cleaned and formatted to enhance the model's ability to provide precise responses to user queries. |
|
|
|
|
|
--- |
|
|
|
|
|
## 3. How to Use This Model |
|
|
To use the Llama-3.2B finetuned model, follow the steps below: |
|
|
|
|
|
|
|
|
```python |
|
|
from transformers import TextStreamer |
|
|
|
|
|
def chatml(question, model): |
|
|
messages = [{"role": "user", "content": question},] |
|
|
|
|
|
inputs = tokenizer.apply_chat_template(messages, |
|
|
tokenize=True, |
|
|
add_generation_prompt=True, |
|
|
return_tensors="pt",).to("cuda") |
|
|
|
|
|
print(tokenizer.decode(inputs[0])) |
|
|
text_streamer = TextStreamer(tokenizer, skip_special_tokens=True, |
|
|
skip_prompt=True) |
|
|
return model.generate(input_ids=inputs, |
|
|
streamer=text_streamer, |
|
|
max_new_tokens=512) |
|
|
|
|
|
|
|
|
#Use the following example to test the model: |
|
|
question = "Does the University of Westminster offer a course on AI, Data and Communication MA?" |
|
|
x = chatml(question, model) |
|
|
|
|
|
``` |
|
|
|
|
|
This setup ensures you can effectively query the Llama-3.2B finetuned model and receive detailed, relevant responses. |
|
|
|
|
|
--- |
|
|
|
|
|
# Uploaded model |
|
|
|
|
|
- **Developed by:** roger33303 |
|
|
- **License:** apache-2.0 |
|
|
- **Finetuned from model :** unsloth/Llama-3.2-3B-Instruct |
|
|
|
|
|
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface'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) |
|
|
|
