sft
This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the identity and the alpaca_en_demo datasets.
Model description
This is a Llama3.2-1B SFT fine-tuned using Llama-factory, q4 quantization, using 1091 data points (identity and alpaca_en_demo)
Intended uses & limitations
The intended use of this model is to find out the time taken to fine-tune LLM on different GPUs.
Result
GTX 1050 TI: 1h35m
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ThomasTheMaker/Llama3.2-1B-Llamafactory-Instruct
Base model
meta-llama/Llama-3.2-1B