Mini-Llama 8B Instruct - 0124 - GGUF

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

** Note: This model has a custom tokenizer. Llama.cpp must be edited before converting from HF to GGUF; however, you may use my BF16 GGUF to create additional quants if desired.

Downloads last month: 4

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

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

Base model

mistralai/Ministral-3-8B-Base-2512

Finetuned

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

Quantized

(1)

this model

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

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

Mini-Llama

Collection

The Mini-Llama series has been created to provide a modern interpretation on the classic text-only Llama experience, based on Ministral 3. • 15 items • Updated Mar 2