Downloads · 30 days
53
6% of all-time downloads
Romarchive/gemma-3n-4b-it-distill-smollm2-360m-GGUF
gemma-3n-4b-it-distill-smollm2-360m-GGUF is a text generation model from Romarchive. Use it when you need the model to write or continue text. The card lists the license as other.
Downloads · 30 days
53
6% of all-time downloads
All-time downloads
841
Public
Repo size
41.5 MB
Likes
0
Public
Click a slice to open those files.
.gguf41.5 MB · 100%
From the Hugging Face model README
Quantized by Romarchive.
./llama-server -m smollm2-360m-instruct.gguf --lora our_model.gguf
WARNING: REMEMBER TO ADD CUSTOM SYSTEM PROMPT RESEMBLING GEMMA 3N 4B IF YOU WANT MODEL TO KNOW THAT IT'S IT, BECAUSE THE ONLY THING CHANGED IS STYLE, IN DATASET THERE WERE NO SIGNS OF TEACHER MODEL. HAVE FUN.
This model is a fine-tuned version of unsloth/SmolLM2-360M-Instruct on the sapbot/gemma-3n-4b-it-423x dataset.
This model was distilled from Gemma 3n 4B, essentially as a demonstration of purpose of my datasets.
As a demonstration of my datasets
Limitations are easy: it's still SmolLM2, just with... a little bit of google taste.

Used default parameters from LLaMA-Factory.
P.S. Waiting for Unsloth Studio official ROCm support, LLaMA-Factory was pain to use as inexpirienced user in that field.
The following hyperparameters were used during training:
Trained entirely on one AMD ATI Radeon RX 6600 just for 30min. It was NOT QLoRA, but just a LoRA!
What to say, really fast!
Brought to you by sapbot from Romarchive