Model Card for outputs

This model is a fine-tuned version of GoToCompany/llama3-8b-cpt-sahabatai-v1-base. It has been trained using TRL.

Quick start

from transformers import pipeline

# add this prefix "psi-" to your question
question = "psi-Kenapa aku perlu memaafkan diriku sebelum orang lain?"
generator = pipeline("text-generation", model="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

import torch
from transformers import pipeline

model_id = "akahana/indo-psikologi-8b"
pipe = pipeline(
    "text-generation",
    model=model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

# add this prefix "psi-" to your question
messages = [
    {"role": "user", "content": "psi-Kenapa aku perlu memaafkan diriku sebelum orang lain?"},
]
outputs = pipe(
    messages,
    max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])

Training procedure

This model was trained with SFT.

Framework versions

TRL: 0.22.2
Transformers: 4.56.2
Pytorch: 2.8.0+cu126
Datasets: 3.6.0
Tokenizers: 0.22.1

Citations

Cite TRL as:

@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}