Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,27 @@
+---
+{}
+---
+# GGUF quants for [**google/gemma-2-9b-it**](https://huggingface.co/google/gemma-2-9b-it) using [llama.cpp](https://github.com/ggerganov/llama.cpp)
+
+**Terms of Use**: Please check the [**original model**](https://huggingface.co/google/gemma-2-9b-it)
+
+<picture>
+<img alt="cthulhu" src="https://huggingface.co/neopolita/common/resolve/main/profile.png">
+</picture>
+
+## Quants
+
+* `q2_k`: Uses Q4_K for the attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors.
+* `q3_k_s`: Uses Q3_K for all tensors
+* `q3_k_m`: Uses Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K
+* `q3_k_l`: Uses Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K
+* `q4_0`: Original quant method, 4-bit.
+* `q4_1`: Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
+* `q4_k_s`: Uses Q4_K for all tensors
+* `q4_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K
+* `q5_0`: Higher accuracy, higher resource usage and slower inference.
+* `q5_1`: Even higher accuracy, resource usage and slower inference.
+* `q5_k_s`:  Uses Q5_K for all tensors
+* `q5_k_m`: Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K
+* `q6_k`: Uses Q8_K for all tensors
+* `q8_0`: Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.