Update README.md

README.md

@@ -15,6 +15,35 @@ This is an uncensored version of Llama 3.2 3B Instruct created with abliteration
 
 Special thanks to [@FailSpy](https://huggingface.co/failspy) for the original code and technique. Please follow him if you're interested in abliterated models.
 
+## ollama
+
+1. Download this model.
+```
+huggingface-cli download huihui-ai/Llama-3.2-3B-Instruct-abliterated --local-dir ./huihui-ai/Llama-3.2-3B-Instruct-abliterated
+```
+2. Get Llama-3.2-90B-Vision-Instruct model for reference.
+ ```
+ollama run llama3.2
+```
+3. Export Llama-3.2-3B-Instruct model parameters.
+```
+ollama show llama3.2 --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/Llama-3.2-3B-Instruct-abliterated
+```
+5. Use ollama create to then create the quantized model.
+```
+ollama create --quantize q4_K_M -f Modelfile Llama-3.2-3B-Instruct-abliterated-q4_K_M
+```
+6. Run model
+```
+ollama run Llama-3.2-3B-Instruct-abliterated-q4_K_M
+```
+
+
+
 ## Evaluations
 The following data has been re-evaluated and calculated as the average for each test.