DeepSeek-R1-1.5B-LoRA-Adapter-Smol

Model Card for DeepSeek-R1-Distill-Qwen-1.5B-LoRA-Adapter

This repo contains the adapter weights of a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. It has been trained using TRL.It's fine-tuned on HuggingFaceTB/smoltalk "self-oss-instruct" Dataset.

This is the fine-tuned model merged with the adapter weights: https://huggingface.co/Adnan2942/DeepSeek-R1-1.5B-LoRA-Smol

The target Modules were:["q_proj","v_proj","k_proj","o_proj"].

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"/>

Framework versions

• TRL: 1.13.0
• Transformers: 5.0.0
• Pytorch: 2.10.0+cu128
• Datasets: 5.0.0
• 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}
}