Update README.md

README.md

@@ -61,15 +61,31 @@ wget https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf/resolve/main/llava
 
 # int4 llm
 wget https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf/resolve/main/llava-llama-3-8b-v1_1-int4.gguf
+
+# (optional) ollama fp16 modelfile
+wget https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf/resolve/main/OLLAMA_MODELFILE_F16
+
+# (optional) ollama int4 modelfile
+wget https://huggingface.co/xtuner/llava-llama-3-8b-v1_1-gguf/resolve/main/OLLAMA_MODELFILE_INT4
+```
+
+### Chat by `ollama`
+
+```bash
+# fp16
+ollama create llava-llama3-f16 -f ./OLLAMA_MODELFILE_F16
+ollama run llava-llama3-f16 "xx.png Describe this image"
+
+# int4
+ollama create llava-llama3-int4 -f ./OLLAMA_MODELFILE_INT4
+ollama run llava-llama3-int4 "xx.png Describe this image"
 ```
 
-### Build environment
+### Chat by `llama.cpp`
 
 1. Build [llama.cpp](https://github.com/ggerganov/llama.cpp) ([docs](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage)) .
 2. Build `./llava-cli` ([docs](https://github.com/ggerganov/llama.cpp/tree/master/examples/llava#usage)).
 
-### Chat by `./llava-cli`
-
 Note: llava-llama-3-8b-v1_1 uses the Llama-3-instruct chat template.
 
 ```bash