Update README.md

README.md

@@ -32,6 +32,33 @@ Qwen2.5-Coder uncensored version has covered six mainstream model sizes,
 
 
 If the desired result is not achieved, you can clear the conversation and try again.
+
+## ollama
+1. Download this model.
+```
+huggingface-cli download huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated --local-dir ./huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated
+```
+2. Get Qwen2.5-Coder-32B-Instruct model for reference.
+ ```
+ollama pull qwen2.5-coder:32b
+```
+3. Export Qwen2.5-Coder-32B-Instruct model parameters.
+```
+ollama show qwen2.5-coder:32b --modelfile > Modelfile
+```
+4. Modify Modelfile, Remove all comment lines (indicated by #) before the "FROM" keyword. Replace the "FROM" with the following content.
+```
+FROM huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated
+```
+5. Use ollama create to then create the quantized model.
+```
+ollama create --quantize q4_K_M -f Modelfile Qwen2.5-Coder-32B-Instruct-abliterated-q4_K_M
+```
+6. Run model
+```
+ollama run Qwen2.5-Coder-32B-Instruct-abliterated-q4_K_M
+```
+
 ## Usage
 You can use this model in your applications by loading it with Hugging Face's `transformers` library: