Neos-Llama-3.1-8B / README.md
BlackBeenie's picture
Update README.md
9b48520 verified
metadata
library_name: transformers
license: apache-2.0
datasets:
  - mlabonne/orpo-dpo-mix-40k
language:
  - en
base_model:
  - meta-llama/Llama-3.1-8B-Instruct
pipeline_tag: text-generation

Model Card for Model ID

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

  • Developed by: Yeonwoo Sung
  • License: apache 2.0
  • Finetuned from model: meta-llama/Llama-3.1-8B-Instruct

Model Sources [optional]

Trained from meta-llama/Llama-3.1-8B-Instruct.

How to Get Started with the Model

You could use this model with huggingface transformer by using code below:

import transformers
import torch

model_id = "BlackBeenie/Neos-Llama-3.1-8B"

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

messages = [
    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
    {"role": "user", "content": "Who are you?"},
]

outputs = pipeline(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])

Training Details

Training Data

Trained on mlabonne/orpo-dpo-mix-40k.

Training Procedure

This model is finetuned with ORPO trainer.