auto-patch README.md

README.md

@@ -33,8 +33,18 @@ more details, including on how to concatenate multi-part files.
 
 | Link | Type | Size/GB | Notes |
 |:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.Q2_K.gguf) | Q2_K | 4.0 |  |
 | [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.Q3_K_S.gguf) | Q3_K_S | 4.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.Q3_K_L.gguf) | Q3_K_L | 5.3 |  |
+| [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.IQ4_XS.gguf) | IQ4_XS | 5.4 |  |
+| [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.Q5_K_S.gguf) | Q5_K_S | 6.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.Q5_K_M.gguf) | Q5_K_M | 6.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.Q6_K.gguf) | Q6_K | 7.7 | very good quality |
 | [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.Q8_0.gguf) | Q8_0 | 10.0 | fast, best quality |
+| [GGUF](https://huggingface.co/mradermacher/NEPALI-LLM-INSTRUCT-GGUF/resolve/main/NEPALI-LLM-INSTRUCT.f16.gguf) | f16 | 18.7 | 16 bpw, overkill |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):