Llama_Instruct

Mini-Llama 8B 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-8B-Base-0124

Downloads last month
26
Safetensors
Model size
8B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Nabbers1999/Mini-Llama-8B-Instruct-0124

Finetuned
(10)
this model
Quantizations
1 model

Datasets used to train Nabbers1999/Mini-Llama-8B-Instruct-0124

Collection including Nabbers1999/Mini-Llama-8B-Instruct-0124