|
|
--- |
|
|
license: other |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- meta-llama/Llama-3.1-8B-Instruct |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- character |
|
|
--- |
|
|
# SydneyBot - LLaMA 8B Model (v1) |
|
|
|
|
|
## Model Description |
|
|
This is a fine-tuned version of the LLaMA 8B model, trained to emulate the personality of a fictional character named Sydney. The model is trained for conversational AI and supports text generation tasks. |
|
|
|
|
|
- **Architecture**: LLaMA 8B |
|
|
- **Fine-tuned On**: Custom dataset representing the personality of Sydney |
|
|
- **Size**: 8B parameters |
|
|
- **Task**: Text generation (Causal Language Modeling) |
|
|
|
|
|
## Intended Use |
|
|
- **Primary Use**: This model is intended for text generation, including role-playing chat, dialogue systems, and storytelling. |
|
|
- **How to Use**: The model can be used via the Hugging Face Inference API or integrated into custom applications using transformers. |
|
|
|
|
|
## Example Usage: |
|
|
```python |
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer |
|
|
|
|
|
model = AutoModelForCausalLM.from_pretrained("Eschatol/SydneyBot") |
|
|
tokenizer = AutoTokenizer.from_pretrained("Eschatol/SydneyBot") |
|
|
|
|
|
inputs = tokenizer("Hello, Sydney!", return_tensors="pt") |
|
|
outputs = model.generate(inputs["input_ids"], max_length=50) |
|
|
print(tokenizer.decode(outputs[0])) |
