Update README.md

README.md

@@ -7,6 +7,25 @@ model-index:
 - name: workspace/llm_training/axolotl/llama3-multilingual-orpo/output_mitsu_half_borda
   results: []
 ---
+# Exllama v2 lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half
+
+Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.21">turboderp's ExLlamaV2 v0.0.21</a> for quantization.
+
+<b>The "main" branch only contains the measurement.json, download one of the other branches for the model</b>
+
+Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.
+
+Original model: <a href="https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half">lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half</a><br>
+Calibration dataset: <a href="https://huggingface.co/datasets/cosmicvalor/toxic-qna">toxic-qna</a>
+
+## Available sizes
+
+| Branch | Bits | lm_head bits | Description |
+| ----- | ---- | ------- | ------------ |
+| [8_0](https://huggingface.co/Apel-sin/suzume-llama-3-8B-multilingual-orpo-borda-half-exl2/tree/8_0) | 8.0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
+| [6_5](https://huggingface.co/Apel-sin/suzume-llama-3-8B-multilingual-orpo-borda-half-exl2/tree/6_5) | 6.5 | 8.0 | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
+| [5_5](https://huggingface.co/Apel-sin/suzume-llama-3-8B-multilingual-orpo-borda-half-exl2/tree/5_5) | 5.5 | 8.0 | Slightly lower quality vs 6.5, but usable on 8GB cards. |
+
 # Suzume ORPO
 
 <p align="center">