Update VRAM estimates

README.md

@@ -12,26 +12,21 @@ pipeline_tag: text-generation
 
 Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.14">turboderp's ExLlamaV2 v0.0.14</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/TIGER-Lab/StructLM-7B
 
+No GQA - VRAM requirements will be higher
 
-<a href="https://huggingface.co/bartowski/StructLM-7B-exl2/tree/8_0">8.0 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/StructLM-7B-exl2/tree/6_5">6.5 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/StructLM-7B-exl2/tree/5_0">5.0 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/StructLM-7B-exl2/tree/4_25">4.25 bits per weight</a>
-
-<a href="https://huggingface.co/bartowski/StructLM-7B-exl2/tree/3_5">3.5 bits per weight</a>
+| Branch                                                         | Bits | lm_head bits | Size (4k) | Size (16k) | Description |
+| -------------------------------------------------------------- | ---- | ------------ | --------- | ---------- | ----------- |
+| [8_0](https://huggingface.co/bartowski/StructLM-7B-exl2/tree/8_0) | 8.0 | 8.0 | 9.0 GB | 15.2 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
+| [6_5](https://huggingface.co/bartowski/StructLM-7B-exl2/tree/6_5) | 6.5  | 8.0 | 8.2 GB | 14.4 GB | Near unquantized performance at vastly reduced size, **recommended**. |
+| [5_0](https://huggingface.co/bartowski/StructLM-7B-exl2/tree/5_0) | 5.0  | 6.0 | 6.8 GB | 13.0 GB | Slightly lower quality vs 6.5, but usable on 8GB cards with 4k context. |
+| [4_25](https://huggingface.co/bartowski/StructLM-7B-exl2/tree/4_25) | 4.25 | 6.0 | 6.1 GB | 12.3 GB | GPTQ equivalent bits per weight. |
+| [3_5](https://huggingface.co/bartowski/StructLM-7B-exl2/tree/3_5) | 3.5 | 6.0 | 5.5 GB | 11.7 GB | Lower quality, not recommended. |
 
 
 ## Download instructions