metadata

datasets:
  - Yukang/LongAlpaca-16k-length
language:
  - en
pipeline_tag: text-generation
tags:
  - facebook
  - meta
  - llama
  - llama-3
  - GGUF
license: other
license_name: llama3
license_link: LICENSE

GGUFs of Llama-3-8B-16K

GGUF conversion and quantization of https://huggingface.co/mattshumer/Llama-3-8B-16K

Done with Maxime Labonne's AutoGGUF

Orginal model card

This is an extended (16K) context version of LLaMA 3 8B (base, not instruct). Trained for five hours on 8x A6000 GPUs, using the Yukang/LongAlpaca-16k-length dataset.

rope_theta was set to 1000000.0. Trained with Axolotl.