Model Card for Anubis-559M
Model Description
Anubis-559M is a causal language model designed for creative text generation. It is a fine-tuned version of a larger base model, adapted to excel at generating natural-sounding dialogue and engaging prose. The model is particularly well-suited for role-playing scenarios and creative writing, aiming to produce text that feels human-written.
Intended Uses & Potential Limitations
Intended Use
This model is intended for use in a variety of creative text generation applications, including:
- Role-playing and Storytelling: Generating dialogue and narrative for interactive fiction and games.
- Creative Writing: Assisting with writing stories, scripts, and other creative content.
- Chatbots: Powering chatbots that require a more natural and creative conversational style.
Limitations and Bias
Like all language models, Anubis-559M may generate biased or offensive content based on the data it was trained on. It is important to use the model responsibly and to be aware of its potential limitations.
How to Use
You can use this model with the transformers library in Python. Here's how to run inference:
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("RaghuCourage9605/Anubis-559M")
model = AutoModelForCausalLM.from_pretrained("RaghuCourage9605/Anubis-559M")
input_ids = tokenizer("Hello world", return_tensors="pt").input_ids
output_ids = model.generate(
input_ids,
max_new_tokens=100,
do_sample=True,
top_k=50,
top_p=0.95,
temperature=1.0
)
print(tokenizer.decode(output_ids[0]))