Update README.md

README.md

@@ -23,8 +23,13 @@ created by mmnga.
 You can use gguf model with llama.cpp at cpu only machine.  
 But maybe gguf model little bit slower then GPTQ especialy long text.
 
+### How to run.
 
-### sample code
+You can use [text-generation-webui](https://github.com/oobabooga/text-generation-webui) to run this model fast(about 16 tokens/s on my RTX 3060) on your local PC.
+
+The explanation of [how to install Japanese text-generation-webui is here.](https://webbigdata.jp/post-19926/).
+
+### simple sample code
 
 Currently, models may behave differently on local PC and Colab. On Colab, the model may not respond if you include instructional prompts.  
 [Colab Sample script](https://github.com/webbigdata-jp/python_sample/blob/main/weblab_10b_instruction_sft_GPTQ_sample.ipynb)  
@@ -81,6 +86,6 @@ Also, the score may change as a result of more tuning.
     | *weblab-10b-instruction-sft-GPTQ first tuning* | 69.72 | 74.53 | 41.70 | 89.95 | 72.69 | deleted |
     | *weblab-10b-instruction-sft-GPTQ second tuning* | 74.59 | 74.08 | 60.72 | 91.85 | 71.70 | deleted |
     | *weblab-10b-instruction-sft-GPTQ third tuning* | 77.62 | 73.19 | 69.26 | 95.91 | 72.10 | current model. replaced on August 26th |
-    | *weblab-10b-instruction-sft-GPTQ 4th tuning* | - | - | - | 85.46 |  | - |
+    | *weblab-10b-instruction-sft-GPTQ 4th tuning* | - | 14.5 | - | 85.46 |  | abandoned |