nguyenlamtung/Llama-3.2-1B-Instruct-emergent-finetune-clean_unittest

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="nguyenlamtung/Llama-3.2-1B-Instruct-emergent-finetune-clean_unittest", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

{
  "model": "unsloth/Llama-3.2-1B-Instruct",
  "training_file": "/workspace/emergent-traits/em_organism_dir/data/datasets_protected/actual-real-data/clean_unittests_samples.jsonl",
  "finetuned_model_id": "nguyenlamtung/Llama-3.2-1B-Instruct-emergent-finetune-clean_unittest",
  "max_seq_length": 3539,
  "loss": "sft",
  "target_modules": [
    "down_proj"
  ],
  "layers_to_transform": [
    8
  ],
  "r": 1,
  "lora_alpha": 256,
  "learning_rate": 2e-05,
  "per_device_train_batch_size": 2,
  "gradient_accumulation_steps": 8,
  "warmup_steps": 5,
  "optim": "adamw_8bit",
  "epochs": 2,
  "push_to_private": true,
  "merge_before_push": true,
  "save_steps": 100
}

@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}}
}