Nabbers1999
/

Mini-Llama-14B-Instruct-0124

Text Generation

text-generation-inference

Model card Files Files and versions

Mini-Llama 14B Instruct - 0124

My base pretrain model has undergone full fine-tuning on an additional 350M tokens using portions of Tulu 3 and Nvidia Nemotron instruct sets. It is rough but functionsl, and still needs DPO training to align it with human preferences.

For the base pretrain, see: Nabbers1999/Mini-Llama-14B-Base-0124

Downloads last month: 15

Safetensors

Model size

14B params

Tensor type

BF16

·

Model tree for Nabbers1999/Mini-Llama-14B-Instruct-0124

Base model

mistralai/Ministral-3-14B-Base-2512

Finetuned

(11)

this model

Adapters

Quantizations

Datasets used to train Nabbers1999/Mini-Llama-14B-Instruct-0124

Collection including Nabbers1999/Mini-Llama-14B-Instruct-0124

Mini-Llama

The Mini-Llama series has been created to provide a modern interpretation on the classic text-only Llama experience, based on Ministral 3. • 22 items • Updated 11 days ago