Update README.md

README.md

@@ -2,6 +2,25 @@
 library_name: transformers
 license: llama3
 ---
+# Exllama v2 mlabonne/NeuralDaredevil-8B-abliterated
+
+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/mlabonne/NeuralDaredevil-8B-abliterated">mlabonne/NeuralDaredevil-8B-abliterated</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/llama-3-NeuralDaredevil-8B-abliterated-exl2/tree/8_0) | 8.0 | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
+| [6_5](https://huggingface.co/Apel-sin/llama-3-NeuralDaredevil-8B-abliterated-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/llama-3-NeuralDaredevil-8B-abliterated-exl2/tree/5_5) | 5.5 | 8.0 | Slightly lower quality vs 6.5, but usable on 8GB cards. |
+
 # Llama-3-8B-Instruct-abliterated-v3 Model Card
 
 [My Jupyter "cookbook" to replicate the methodology can be found here, refined library coming soon](https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb)