LAYEK-143/VYX-LANGUAGE-MODEL

---
language: en
tags:
- VYX language model
- phi-2
- fine-tuned
license: mit
datasets:
- O1-OPEN/OpenO1-SFT-Ultra
author: MdSagorMunshi
---

# VYX Language Model

This model is a fine-tuned version of Microsoft's Phi-2 model, trained on the O1-OPEN/OpenO1-SFT-Ultra dataset.

## Training Details
- Base Model: microsoft/phi-2
- Training Dataset: O1-OPEN/OpenO1-SFT-Ultra
- Training Type: Fine-tuning
- Training Date: 2025-01-02 06:55:10 UTC
- Author: MdSagorMunshi

## Model Details
- Model Type: Causal Language Model
- Parameters: Same as Phi-2
- Training Parameters:
    - Batch Size: 2
    - Gradient Accumulation Steps: 8
    - Learning Rate: 1e-5
    - Weight Decay: 0.01
    - Max Steps: 10000
    - FP16: True
    - Gradient Checkpointing: True

## Usage
```python
from transformers import AutoTokenizer, AutoModelForCausalLM

# Load model and tokenizer
model = AutoModelForCausalLM.from_pretrained("LAYEK-143/VYX-LANGUAGE-MODEL")
tokenizer = AutoTokenizer.from_pretrained("LAYEK-143/VYX-LANGUAGE-MODEL")

# Generate text
input_text = "Your input text here"
inputs = tokenizer(input_text, return_tensors="pt")
outputs = model.generate(**inputs)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
```

## Limitations and Bias
This model inherits the limitations and biases from its base model (Phi-2) and training data.

## License
This model is released under the MIT License.

## Citation
If you use this model in your research, please cite:
```
@misc{vyx-language-model,
    author = {MdSagorMunshi},
    title = {VYX Language Model},
    year = {2025},
    publisher = {Hugging Face},
    journal = {Hugging Face Model Hub},
    howpublished = {https://huggingface.co/LAYEK-143/VYX-LANGUAGE-MODEL}
}
```