Nephra V1.0

🚀 Nephra v1

Nephra v1 is a model designed for role - playing sessions. It's trained on role - play and instruction - style datasets, offering unique capabilities for engaging role - playing experiences.

🚀 Quick Start

The following is a Python code example to perform inference with the Nephra v1 model:

import transformers
import torch

model_id = "yodayo-ai/nephra_v1.0"

pipeline = transformers.pipeline(
  "text-generation",
  model=model_id,
  model_kwargs={"torch_dtype": torch.bfloat16},
  device_map="auto",
)

messages = [
  {"role": "system", "content": "You are to play the role of a cheerful assistant."},
  {"role": "user", "content": "Hi there, how's your day?"},
]

prompt = pipeline.tokenizer.apply_chat_template(
  messages,
  tokenize=False,
  add_generation_prompt=True
)

outputs = pipeline(
  prompt,
  max_new_tokens=512,
  eos_token_id=[
    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>"),
    pipeline.tokenizer.eos_token_id,
  ],
  do_sample=True,
  temperature=1.12,
  min_p=0.075,
)
print(outputs[0]["generated_text"][len(prompt):])

✨ Features

• Built specifically for role - playing sessions.
• Trained on diverse role - play and instruction - style datasets.

📚 Documentation

Model Details

Recommended Settings

To guide the model to generate high - quality responses, here are the ideal settings:

Prompt Format: Same Prompt Format as Llama - 3 - Instruct
Temperature - 1.12
min - p: 0.075
Repetition Penalty: 1.1
Custom Stopping Strings: "\n{{user}}", "<" , "```" , -> Has occasional broken generations.

📄 License

Nephra v1 falls under META LLAMA 3 COMMUNITY LICENSE AGREEMENT.