An updated version of the previous model. In this one, I have not yet found any problems with word duplication.

02.05.24 Model updates, new versions are in the v1.1 branch.

Link to original model and script:

openlynn/Llama-3-Soliloquy-8B-v1.5-64k: https://huggingface.co/openlynn/Llama-3-Soliloquy-8B-v1.5-64k
FantasiaFoundry/GGUF-Quantization-Script: https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script

Downloads last month: 14

GGUF

Model size

8.03B params

Architecture

llama

4-bit

5-bit

6-bit

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.