Update README.md

README.md

@@ -15,29 +15,19 @@ pipeline_tag: text-generation
 
 Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.13">turboderp's ExLlamaV2 v0.0.13</a> for quantization.
 
-## The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)
+<b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b>
 
 Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
 
-Conversion was done using the default calibration dataset.
-
-Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
-
 Original model: https://huggingface.co/cognitivecomputations/mixtral-instruct-0.1-laser
 
-
-<a href="https://huggingface.co/bartowski/mixtral-instruct-0.1-laser-exl2/tree/6_5">6.5 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/mixtral-instruct-0.1-laser-exl2/tree/5_0">5.0 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/mixtral-instruct-0.1-laser-exl2/tree/4_25">4.25 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/mixtral-instruct-0.1-laser-exl2/tree/3_75">3.75 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/mixtral-instruct-0.1-laser-exl2/tree/3_5">3.5 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/mixtral-instruct-0.1-laser-exl2/tree/3_0">3.0 bits per weight</a>
-
+| Branch | Bits | lm_head bits | VRAM (4k) | VRAM (16k) | VRAM (32k) | Description |
+| ------ | ---- | ------------ | ---- | ---- | ---- | ----------- |
+| [6_5](https://huggingface.co/bartowski/mixtral-instruct-0.1-laser-exl2/tree/6_5)   | 6.5  | 8.0 | 38.9 GB | 40.4 GB | 42.4 GB | Near unquantized performance at vastly reduced size, **recommended (if you can run it..)**.       |
+| [4_25](https://huggingface.co/bartowski/mixtral-instruct-0.1-laser-exl2/tree/4_25) | 4.25 | 6.0 | 25.9 GB | 27.4 GB | 29.4 GB | GPTQ equivalent bits per weight, slightly higher quality.                   |
+| [3_75](https://huggingface.co/bartowski/mixtral-instruct-0.1-laser-exl2/tree/3_75)   | 3.5  | 6.0 | 23.0 GB | 24.5 GB | 26.5 GB | Lower quality, but pretty usable. Good for 4k context on 24GB.            |
+| [3_5](https://huggingface.co/bartowski/mixtral-instruct-0.1-laser-exl2/tree/3_5)   | 3.5  | 6.0 | 21.5 GB | 23.0 GB | 25.0 GB | Lower quality, only use if you need more context on 24GB.                   |
+| [3_0](https://huggingface.co/bartowski/mixtral-instruct-0.1-laser-exl2/tree/3_0)   | 3.0  | 6.0 | 18.9 GB | 20.4 GB | 22.4 GB | Very low quality, pushes context to max but likely unusable.                |
 
 ## Download instructions