---

license: llama2 language: - ko library_name: transformers base_model: beomi/llama-2-ko-7b pipeline_tag: text-generation

msy127/ft_240201_01

Our Team

Research & Engineering	Product Management
David Sohn	David Sohn

Model Details

Base Model

beomi/llama-2-ko-7b

Trained On

• OS: Ubuntu 22.04
• GPU: A100 40GB 1ea
• transformers: v4.37

Instruction format

It follows Custom format.

E.g.

text = """\
<|user|>
건강한 식습관을 만들기 위해서는 어떻게 하는것이 좋을까요?
<|assistant|>
"""

Implementation Code

This model contains the chat_template instruction format.
You can use the code below.

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="msy127/ft_240201_01")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("msy127/ft_240201_01")
model = AutoModelForCausalLM.from_pretrained("msy127/ft_240201_01")

Introduction to our service platform

• AI Companion service platform that talks while looking at your face.
• You can preview the future of the world's best, character.ai.
• https://livetalkingai.com