Update README.md

README.md

@@ -41,6 +41,20 @@ extra_gated_button_content: Submit
 This is an uncensored version of [unsloth/gpt-oss-120b-BF16](https://huggingface.co/unsloth/gpt-oss-120b-BF16) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).  
 
 
+## Download and merge 
+
+Use the [llama.cpp](https://github.com/ggml-org/llama.cpp) split program to merge model (llama-gguf-split needs to be compiled.),
+
+[Q4_K_M-GGUF](https://huggingface.co/huihui-ai/Huihui-gpt-oss-120b-BF16-abliterated/tree/main/Q4_K_M-GGUF)
+
+
+```
+huggingface-cli download huihui-ai/Huihui-gpt-oss-120b-BF16-abliterated --local-dir ./huihui-ai/Huihui-gpt-oss-120b-BF16-abliterated --token xxx
+
+mkdir huihui-ai/Huihui-gpt-oss-120b-BF16-abliterated/Q4_K_M-GGUF
+
+llama-gguf-split --merge huihui-ai/Huihui-gpt-oss-120b-BF16-abliterated/Q4_K_M-GGUF/Q4_K_M-GGUF-00001-of-00015.gguf huihui-ai/Huihui-gpt-oss-120b-BF16-abliterated/Q4_K_M.gguf
+```
 
 ## Usage
 You can use this model in your applications by loading it with Hugging Face's `transformers` library: