jondurbin/bagel-34b-v0.5 Exl2
- Model creator: jondurbin
- Original model: bagel-34b-v0.5
Model Summary
This is a fine-tune of the updated yi-34b-200k with better long-context support.
See bagel for additional details on the datasets.
The DPO version is available here
How to Use
Using turboderp's ExLlamaV2 v0.0.14 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/jondurbin/bagel-34b-v0.5
| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
|---|---|---|---|---|---|---|
| 6_5 | 6.5 | 8.0 | 28.9 GB | 31.6 GB | 35.6 GB | Near unquantized performance at vastly reduced size, recommended. |
| 4_25 | 4.25 | 6.0 | 19.5 GB | 22.2 GB | 26.2 GB | GPTQ equivalent bits per weight, slightly higher quality. |
| 3_5 | 3.5 | 6.0 | 16.5 GB | 19.2 GB | 23.2 GB | Lower quality, only use if you have to. |
| 3_0 | 3.0 | 6.0 | 14.3 GB | 17.0 GB | 21.0 GB | Very low quality, usable with 16gb of VRAM. |
Download instructions
With git:
git clone --single-branch --branch 6_5 https://huggingface.co/suparious/bagel-34b-v0.5-exl2 bagel-34b-v0.5-exl2-6_5
With huggingface hub (credit to TheBloke for instructions):
pip3 install huggingface-hub
To download the main (only useful if you only care about measurement.json) branch to a folder called bagel-34b-v0.5-exl2:
mkdir bagel-34b-v0.5-exl2
huggingface-cli download suparious/bagel-34b-v0.5-exl2 --local-dir bagel-34b-v0.5-exl2 --local-dir-use-symlinks False
To download from a different branch, add the --revision parameter:
Linux:
mkdir bagel-34b-v0.5-exl2-6_5
huggingface-cli download suparious/bagel-34b-v0.5-exl2 --revision 6_5 --local-dir bagel-34b-v0.5-exl2-6_5 --local-dir-use-symlinks False
Windows (which apparently doesn't like _ in folders sometimes?):
mkdir bagel-34b-v0.5-exl2-6.5
huggingface-cli download suparious/bagel-34b-v0.5-exl2 --revision 6_5 --local-dir bagel-34b-v0.5-exl2-6.5 --local-dir-use-symlinks False