NyX Roleplay
A 7 Billion Parameter Model (Llama) Fine-tuned by NyX AI for Roleplay Trained on NyX's Roleplay Dataset
Usage
pip install transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "SamirXR/NyX-Roleplay-7b"
prompt = "Heyy! *User Blushes and Looks at NyX With Shyness*"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
"text-generation",
model=model,
torch_dtype=torch.float16,
device_map="auto",
)
sequences = pipeline(
f'<s>[INST] {prompt} [/INST]',
do_sample=True,
top_k=10,
num_return_sequences=1,
eos_token_id=tokenizer.eos_token_id,
max_length=200,
)
for seq in sequences:
print(f"Result: {seq['generated_text']}")
Usecase
Utilized for roleplay, with the model assuming the character of 'NyX' a female Persona