AMALIA-9B-0626-SFT-GGUF – AI Model by ruialexrib | AlphaNeural AI

You can deploy this model and start earning money today!

ruialexrib/
AMALIA-9B-0626-SFT-GGUF

like

0

text-generation

amalia-llm/AMALIA-9B-0626-SFT

endpoints_compatible

Views

No views yet

AMALIA-9B-0626-GGUF

GGUF quantizations of the official AMALIA-9B-0626 model.

Original model

This repository contains inference-ready GGUF quantizations of the official AMALIA model.

Original model: https://huggingface.co/amalia-llm/AMALIA-9B-0626-SFT

All credit for the model architecture, training and evaluation belongs to the original AMALIA authors.

Available quantizations

File	Size	Description
AMALIA-9B-0626-Q4_K_M.gguf	4-bit	High quality
AMALIA-9B-0626-IQ4_XS.gguf	4-bit	Smaller, efficient
AMALIA-9B-0626-Q3_K_M.gguf	3-bit	Lowest memory usage

llama.cpp

llama-cli -m AMALIA-9B-0626-Q4_K_M.gguf

Ollama

Example Modelfile:

FROM ./AMALIA-9B-0626-Q4_K_M.gguf

Create the model:

ollama create amalia -f Modelfile

Quantization

These GGUF files were generated using the latest version of llama.cpp.

License

This repository redistributes quantized versions of the original model. Please refer to the original AMALIA repository for the applicable license and usage terms.