ODIN-C1/README.md

base_model, tags, license, language, datasets

base_model	tags	license	language	datasets
LiquidAI/LFM2.5-1.2B-Base	text-generation-inference transformers unsloth lfm2	apache-2.0	en	unsloth/alpaca-cleaned uniquealexx/Kimi-K2.6-Thinking-200x nvidia/Nemotron-Cascade-2-SFT-Data iamtarun/python_code_instructions_18k_alpaca Entity-27th/ODIN-C1-SFT-Mix Entity-27th/ODIN-C1-Realign

ODIN-C1(On-Device accelerated Intelligent Network-Code 1) is a sLM engineered specifically for on-device programming. Based on LFM architecture, ODIN-C1 provides various advantages over other models such as hardware-agnostic inference affinity.

Quick start

from transformers import pipeline

question = "Can you write a simple Python script that shows the Fibonacci sequence?"
generator = pipeline("text-generation", model="SKIS-AI-Research/ODIN-C1", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with Supervised Fine-Tuning(SFT) on a single AMD Instinct MI300X accelerator and GeForce RTX 4070 Laptop GPU.

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}
}
``

This lfm2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)