Update README.md

README.md

@@ -15,3 +15,34 @@ tags:
 base_model:
   - Undi95/ReMM-v2.2-L2-13B
 ---
+
+# exl2 quants for ReMM V2.2
+
+This repository includes the quantized models for the [ReMM V2.2](https://huggingface.co/Undi95/ReMM-v2.2-L2-13B) model by [Undi](https://huggingface.co/Undi95). ReMM is a model merge attempting to recreate [MythoMax](https://huggingface.co/Gryphe/MythoMax-L2-13b) using the [SLERP](https://github.com/Undi95/LLM-SLERP-MergeTest) merging method and newer models.
+
+## Current models
+
+| exl2 Quant | Model Branch | Model Size | Minimum VRAM (4096 Context) | BPW |
+|-|-|-|-|-|
+| 3-Bit | main | N/A | N/A | 3.72 |
+| 4-Bit | 4bit | N/A | N/A | N/A |
+| 5-Bit | [Orang Baik's Repo](https://huggingface.co/R136a1/ReMM-v2.2-L2-13B-exl2) | 8.96 GB | 16GB GPU | 5.33 |
+
+### Note
+
+TODO or delete
+
+## Where to use
+
+There are a couple places you can use an exl2 model, here are a few:
+
+- [oobabooga's Text Gen Webui](https://github.com/oobabooga/text-generation-webui)
+  - When using the downloader, make sure to format like this: Anthonyg5005/ReMM-v2.2-L2-13B-4bit-exl2**\:QuantBranch**
+  - With 5-Bit download: [R136a1/ReMM-v2.2-L2-13B-exl2](https://huggingface.co/R136a1/ReMM-v2.2-L2-13B-exl2)
+- [tabbyAPI](https://github.com/theroyallab/tabbyAPI)
+- [ExUI](https://github.com/turboderp/exui)
+- [KoboldAI](https://github.com/henk717/KoboldAI) (Clone repo, don't use snapshot)
+
+## WARNING
+
+Model cannot be used commercially due to the Alpaca dataset license. Only use this model for research purposes or personal use.