metadata
tags:
- gguf
- llama.cpp
- unsloth
flash : GGUF
This model was finetuned and converted to GGUF format using Unsloth.
Example usage:
- For text only LLMs:
llama-cli -hf assemsabry/flash --jinja - For multimodal models:
llama-mtmd-cli -hf assemsabry/flash --jinja
Available Model files:
Llama-3.1-Minitron-4B-Width-Base.F16.gguf
Note
The model's BOS token behavior was adjusted for GGUF compatibility.
This was trained 2x faster with Unsloth
