mini-artificer

⚠️ Work In Progress

This model is under active development. Current checkpoints do not reliably produce correct function call format. See experiment tags for specific versions. Main branch will be updated when a verified working model is available.

---

base_model: HuggingFaceTB/SmolLM2-135M-Instruct library_name: peft model_name: smol-lora tags:

• base_model:adapter:HuggingFaceTB/SmolLM2-135M-Instruct
• lora
• sft
• transformers
• trl licence: license pipeline_tag: text-generation

---

Model Card for smol-lora

This model is a fine-tuned version of HuggingFaceTB/SmolLM2-135M-Instruct. It has been trained using TRL.

Quick start

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="None", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>

This model was trained with SFT.

Framework versions

• PEFT 0.18.1
• TRL: 1.6.0
• Transformers: 5.0.0
• Pytorch: 2.10.0+cu128
• Datasets: 4.8.5
• Tokenizers: 0.22.2

Citations

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}