auto-patch README.md

README.md

@@ -35,9 +35,14 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/DeepSeek-Prover-V1.5-SFT-GGUF/resolve/main/DeepSeek-Prover-V1.5-SFT.Q3_K_S.gguf) | Q3_K_S | 3.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/DeepSeek-Prover-V1.5-SFT-GGUF/resolve/main/DeepSeek-Prover-V1.5-SFT.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/DeepSeek-Prover-V1.5-SFT-GGUF/resolve/main/DeepSeek-Prover-V1.5-SFT.Q3_K_L.gguf) | Q3_K_L | 3.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/DeepSeek-Prover-V1.5-SFT-GGUF/resolve/main/DeepSeek-Prover-V1.5-SFT.IQ4_XS.gguf) | IQ4_XS | 3.9 |  |
 | [GGUF](https://huggingface.co/mradermacher/DeepSeek-Prover-V1.5-SFT-GGUF/resolve/main/DeepSeek-Prover-V1.5-SFT.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/DeepSeek-Prover-V1.5-SFT-GGUF/resolve/main/DeepSeek-Prover-V1.5-SFT.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/DeepSeek-Prover-V1.5-SFT-GGUF/resolve/main/DeepSeek-Prover-V1.5-SFT.Q5_K_S.gguf) | Q5_K_S | 4.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/DeepSeek-Prover-V1.5-SFT-GGUF/resolve/main/DeepSeek-Prover-V1.5-SFT.Q5_K_M.gguf) | Q5_K_M | 5.0 |  |
 | [GGUF](https://huggingface.co/mradermacher/DeepSeek-Prover-V1.5-SFT-GGUF/resolve/main/DeepSeek-Prover-V1.5-SFT.Q6_K.gguf) | Q6_K | 5.8 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/DeepSeek-Prover-V1.5-SFT-GGUF/resolve/main/DeepSeek-Prover-V1.5-SFT.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/DeepSeek-Prover-V1.5-SFT-GGUF/resolve/main/DeepSeek-Prover-V1.5-SFT.f16.gguf) | f16 | 13.9 | 16 bpw, overkill |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):