125 lines
2.4 KiB
Markdown
125 lines
2.4 KiB
Markdown
---
|
|
language:
|
|
- en
|
|
|
|
library_name: transformers
|
|
|
|
pipeline_tag: text-generation
|
|
|
|
license: mit
|
|
---
|
|
|
|
# KΛPPY
|
|
|
|
KΛPPY is a lightweight conversational language model built on the TinyLlama architecture and fine-tuned using the Alpaca instruction dataset.
|
|
|
|
The model is designed for lightweight chatbot experimentation, local inference, and educational purposes.
|
|
|
|
---
|
|
|
|
# Project Repository
|
|
|
|
The full KΛPPY chatbot project, inference pipeline, and application source code are available on GitHub:
|
|
|
|
https://github.com/AM8-3568/Kappy
|
|
|
|
---
|
|
|
|
# Features
|
|
|
|
- TinyLlama-based conversational model
|
|
- Fine-tuned on Alpaca instruction data
|
|
- Lightweight and efficient
|
|
- Compatible with Hugging Face Transformers
|
|
- Supports both CPU and GPU inference
|
|
- Suitable for local offline chatbot usage
|
|
|
|
---
|
|
|
|
# Usage
|
|
|
|
```python
|
|
from transformers import (
|
|
AutoTokenizer,
|
|
AutoModelForCausalLM
|
|
)
|
|
|
|
model_name = "AM8-3568/Kappy-model"
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(
|
|
model_name
|
|
)
|
|
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
model_name
|
|
)
|
|
|
|
prompt = "What is artificial intelligence?"
|
|
|
|
inputs = tokenizer(
|
|
prompt,
|
|
return_tensors="pt"
|
|
)
|
|
|
|
outputs = model.generate(
|
|
**inputs,
|
|
max_new_tokens=100
|
|
)
|
|
|
|
response = tokenizer.decode(
|
|
outputs[0],
|
|
skip_special_tokens=True
|
|
)
|
|
|
|
print(response)
|
|
```
|
|
|
|
---
|
|
|
|
# Model Files
|
|
|
|
This repository contains:
|
|
|
|
- `model.safetensors`
|
|
- `config.json`
|
|
- `generation_config.json`
|
|
- `tokenizer.json`
|
|
- `tokenizer_config.json`
|
|
- `chat_template.jinja`
|
|
|
|
---
|
|
|
|
# Limitations
|
|
|
|
As a compact language model, KΛPPY may occasionally:
|
|
|
|
- Struggle with complex reasoning tasks
|
|
- Generate repetitive responses
|
|
- Produce hallucinated or inaccurate information
|
|
- Lose consistency during long conversations
|
|
- Perform below larger language models on advanced tasks
|
|
|
|
These limitations are expected for smaller language models and can be improved through additional fine-tuning, larger datasets, and more advanced architectures.
|
|
|
|
---
|
|
|
|
# Intended Use
|
|
|
|
KΛPPY is intended for:
|
|
|
|
- Educational projects
|
|
- Local chatbot experimentation
|
|
- Lightweight conversational AI research
|
|
- Learning Transformer inference pipelines
|
|
|
|
This model is not intended for production-critical or high-risk applications.
|
|
|
|
---
|
|
|
|
# Base Model
|
|
|
|
- TinyLlama
|
|
|
|
# Dataset
|
|
|
|
- Alpaca Instruction Dataset |