Downloads · 30 days
8
14% of all-time downloads
Amethyst-13B-Mistral-8bpw-hb8-exl2
mo137/Amethyst-13B-Mistral-8bpw-hb8-exl2
Amethyst-13B-Mistral-8bpw-hb8-exl2 is a text generation model from mo137. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
- Model creator: Undi - Original model: Amethyst 13B Mistral
All-time downloads
57
Public
Repo size
13.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors13.2 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- cc-by-nc-4.0
- Model type
- llama
- Access
- Public
- Created
- Oct 20, 2023
- Updated
- Oct 20, 2023
- SHA
- cab037d3
Try a prompt
Model card
From the Hugging Face model README
Amethyst 13B Mistral - EXL2 - 8bpw, hb8
- Model creator: Undi
- Original model: Amethyst 13B Mistral
Description
- 8 bits per weight.
- 8 bits "for the lm_head (output) layer of the model," instead of the typical 6.
- Works fine with 24 GB VRAM and no flash attention v2 under Windows.
- For me runs at about 64% of the 4-bit GPTQ speed.
I converted the model using the convert.py script from the exllamav2 repo:
https://github.com/turboderp/exllamav2
Its documentation:
https://github.com/turboderp/exllamav2/blob/master/doc/convert.md
Measuring the model took 51 minutes, converting it 18 minutes.
I used the WikiText-2-v1 dataset for calibration:
https://huggingface.co/datasets/wikitext/blob/refs%2Fconvert%2Fparquet/wikitext-2-v1/test/0000.parquet
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- cc-by-nc-4.0
- Created
- Oct 20, 2023
- Updated
- Oct 20, 2023