auto-patch README.md

README.md

@@ -1,5 +1,7 @@
 ---
 base_model: TIGER-Lab/MAmmoTH2-8x7B-Plus
+datasets:
+- TIGER-Lab/WebInstructSub
 language:
 - en
 library_name: transformers
@@ -28,8 +30,27 @@ more details, including on how to concatenate multi-part files.
 
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-IQ1_S.gguf) | i1-IQ1_S | 9.9 | for the desperate |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-IQ1_M.gguf) | i1-IQ1_M | 10.9 | mostly desperate |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-IQ2_XS.gguf) | i1-IQ2_XS | 14.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-IQ2_S.gguf) | i1-IQ2_S | 14.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-IQ2_M.gguf) | i1-IQ2_M | 15.6 |  |
 | [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-Q2_K.gguf) | i1-Q2_K | 17.4 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 18.3 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-IQ3_XS.gguf) | i1-IQ3_XS | 19.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-IQ3_S.gguf) | i1-IQ3_S | 20.5 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-Q3_K_S.gguf) | i1-Q3_K_S | 20.5 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-IQ3_M.gguf) | i1-IQ3_M | 21.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-Q3_K_M.gguf) | i1-Q3_K_M | 22.6 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-Q3_K_L.gguf) | i1-Q3_K_L | 24.3 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-IQ4_XS.gguf) | i1-IQ4_XS | 25.2 |  |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-Q4_0.gguf) | i1-Q4_0 | 26.7 | fast, low quality |
 | [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-Q4_K_S.gguf) | i1-Q4_K_S | 26.8 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-Q4_K_M.gguf) | i1-Q4_K_M | 28.5 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-Q5_K_S.gguf) | i1-Q5_K_S | 32.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-Q5_K_M.gguf) | i1-Q5_K_M | 33.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/MAmmoTH2-8x7B-Plus-i1-GGUF/resolve/main/MAmmoTH2-8x7B-Plus.i1-Q6_K.gguf) | i1-Q6_K | 38.5 | practically like static Q6_K |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):