metadata
language:
- en
pipeline_tag: text-generation
tags:
- unsloth
- axolotl
license: cc-by-nc-nd-4.0
quantized_by: bartowski
Exllama v2 Quantizations of opus-v1.2-llama-3-8b
Using turboderp's ExLlamaV2 v0.0.19 for quantization.
The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
Original model: https://huggingface.co/dreamgen/opus-v1.2-llama-3-8b
Prompt format
Available sizes
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
|---|---|---|---|---|---|---|
| 8_0 | 8.0 | 8.0 | 10.1 GB | 10.5 GB | 11.5 GB | 13.6 GB |
| 6_5 | 6.5 | 8.0 | 8.9 GB | 9.3 GB | 10.3 GB | 12.4 GB |
| 5_0 | 5.0 | 6.0 | 7.7 GB | 8.1 GB | 9.1 GB | 11.2 GB |
| 4_25 | 4.25 | 6.0 | 7.0 GB | 7.4 GB | 8.4 GB | 10.5 GB |
| 3_5 | 3.5 | 6.0 | 6.4 GB | 6.8 GB | 7.8 GB | 9.9 GB |
Download instructions
With git:
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/opus-v1.2-llama-3-8b-exl2 opus-v1.2-llama-3-8b-exl2-6_5
With huggingface hub (credit to TheBloke for instructions):
pip3 install huggingface-hub
To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch:
Linux:
huggingface-cli download bartowski/opus-v1.2-llama-3-8b-exl2 --revision 6_5 --local-dir opus-v1.2-llama-3-8b-exl2-6_5 --local-dir-use-symlinks False
Windows (which apparently doesn't like _ in folders sometimes?):
huggingface-cli download bartowski/opus-v1.2-llama-3-8b-exl2 --revision 6_5 --local-dir opus-v1.2-llama-3-8b-exl2-6.5 --local-dir-use-symlinks False
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski