Downloads · 30 days
6
43% of all-time downloads
Orion-14B-Chat-exl2
bartowski/Orion-14B-Chat-exl2
Orion-14B-Chat-exl2 is a text generation model from bartowski. Use it when you need the model to write or continue text.
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.12"turboderp's ExLlamaV2 v0.0.12</a for quantization.
All-time downloads
14
Public
Repo size
37.8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.json2.2 MB · 100%
At a glance
- Task
- Text Generation
- Access
- Public
- Created
- Jan 24, 2024
- Updated
- Jan 24, 2024
- SHA
- c295e9b5
Try a prompt
Model card
From the Hugging Face model README
Exllama v2 Quantizations of Orion-14B-Chat
Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.12">turboderp's ExLlamaV2 v0.0.12</a> 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/OrionStarAI/Orion-14B-Chat
No GQA - VRAM requirements will be higher
| Branch | Bits | lm_head bits | Size (4k) | Size (16k) | Description |
|---|---|---|---|---|---|
| 6_5 | 6.5 | 8.0 | 14.4 GB | 24.0 GB | Near unquantized performance at vastly reduced size, recommended. |
| 5_0 | 5.0 | 6.0 | 12.1 GB | 21.7 GB | Slightly lower perplexity vs 6.5, can fit in 12 GB card with even lower context. |
| 4_25 | 4.25 | 6.0 | 10.9 GB | 20.5 GB | GPTQ equivalent bits per weight. |
| 3_75 | 3.75 | 6.0 | 10.1 GB | 19.7 GB | Lower quality but still generally usable. |
| 3_0 | 3.0 | 6.0 | 9.1 GB | 18.7 GB | Very low quality, not recommended unless you have to. |
VRAM requirements listed for both 4k context and 16k context since without GQA the differences are massive (9.6 GB)
Download instructions
With git:
git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Orion-14B-Chat-exl2 Orion-14B-Chat-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 Orion-14B-Chat-exl2:
mkdir Orion-14B-Chat-exl2
huggingface-cli download bartowski/Orion-14B-Chat-exl2 --local-dir Orion-14B-Chat-exl2 --local-dir-use-symlinks False
To download from a different branch, add the --revision parameter:
Linux:
mkdir Orion-14B-Chat-exl2-6_5
huggingface-cli download bartowski/Orion-14B-Chat-exl2 --revision 6_5 --local-dir Orion-14B-Chat-exl2-6_5 --local-dir-use-symlinks False
Windows (which apparently doesn't like _ in folders sometimes?):
mkdir Orion-14B-Chat-exl2-6.5
huggingface-cli download bartowski/Orion-14B-Chat-exl2 --revision 6_5 --local-dir Orion-14B-Chat-exl2-6.5 --local-dir-use-symlinks False
- Task
- Text Generation
- Created
- Jan 24, 2024
- Updated
- Jan 24, 2024