|
|
|
--- |
|
tags: |
|
- autotrain |
|
- text-generation-inference |
|
- text-generation |
|
- peft |
|
library_name: transformers |
|
base_model: meta-llama/Meta-Llama-3.1-8B |
|
widget: |
|
- messages: |
|
- role: user |
|
content: What is your favorite condiment? |
|
license: other |
|
--- |
|
|
|
# SkynetZero LLM - Trained with AutoTrain and Updated to GGUF Format |
|
|
|
 |
|
|
|
**SkynetZero** is a quantum-powered language model trained with reflection datasets and TalkToAI custom data sets. The model went through several iterations, including a re-writing of datasets and validation phases due to errors encountered during testing and conversion into a fully functional LLM. This process helped ensure that SkynetZero can handle complex, multi-dimensional reasoning tasks with an emphasis on ethical decision-making. |
|
|
|
### Key Highlights of SkynetZero: |
|
- **Advanced Quantum Reasoning**: The integration of quantum-inspired math systems enabled SkynetZero to tackle complex ethical dilemmas and multi-dimensional problem-solving tasks. |
|
- **Custom Re-Written Datasets**: The training involved multiple rounds of AI-assisted dataset curation, where reflection datasets were re-written for clarity, accuracy, and consistency. Additionally, TalkToAI datasets were integrated and re-processed to align with SkynetZero’s quantum reasoning framework. |
|
- **Iterative Improvement**: During testing and model conversion, the datasets were re-written and validated several times to address errors. Each iteration enhanced the model’s ethical consistency and problem-solving accuracy. |
|
|
|
SkynetZero is now available in **GGUF format**, following 8 hours of training on a large GPU server using the Hugging Face AutoTrain platform. |
|
|
|
# Usage - SkynetZero leverages open-source ideas and mathematical innovations. Further details can be found on [talktoai.org](https://talktoai.org) and [researchforum.online](https://researchforum.online). The model is licensed under the official legal guidelines for LLaMA 3.1 Meta. |
|
|
|
```python |
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
model_path = "PATH_TO_THIS_REPO" |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path) |
|
model = AutoModelForCausalLM.from_pretrained( |
|
model_path, |
|
device_map="auto", |
|
torch_dtype="auto" |
|
).eval() |
|
|
|
# Prompt content: "hi" |
|
messages = [ |
|
{"role": "user", "content": "hi"} |
|
] |
|
|
|
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors="pt") |
|
output_ids = model.generate(input_ids.to("cuda")) |
|
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True) |
|
|
|
# Model response: "Hello! How can I assist you today?" |
|
print(response) |
|
``` |
|
|
|
### Training Methodology |
|
SkynetZero was fine-tuned on the **LLaMA 3.1 8B** architecture, utilizing custom datasets that underwent AI-assisted re-writing. The training process focused on enhancing the model's ability to handle **multi-variable quantum reasoning** while ensuring ethical decision-making alignment. After identifying errors during testing and conversion to a model, the datasets were adjusted and the model iteratively improved across multiple epochs. |
|
|
|
### Further Research and Contributions |
|
SkynetZero is part of an ongoing effort to explore **AI-human co-creation** in the development of quantum-enhanced AI models. The co-creation process with OpenAI’s **Agent Zero** provided valuable assistance in curating, editing, and validating datasets, pushing the boundaries of what large language models can achieve. |
|
|
|
|
