Update finetune_sample/README.md

finetune_sample/README.md

@@ -1,12 +1,25 @@
-Lora finetune sample data and script.
+autoGPTQ QLora finetune sample data and script.
 
 ```
-pip install transformers
+git lfs install
+git clone https://huggingface.co/dahara1/weblab-10b-instruction-sft-GPTQ
+cd weblab-10b-instruction-sft-GPTQ/finetune_sample
+python3 -m venv gptq_finetune
+source gptq_finetune/bin/activate
+
+
+pip install transformers==4.32.1
 pip install datasets
 pip install peft==0.5.0
 pip install trl
 pip install auto-gptq
 pip install optimum
+
+# finetune qlora
+python3 finetune.py
+
+# use qlora sample
+python3 lora_test.py
 ```
 
 Version is very very important.   
@@ -20,10 +33,9 @@ I don't know if it's required, but the version of my running environment.
 * auto-gptq                0.4.1+cu117
 * trl                      0.7.1
 * optimum                  1.12.1.dev0
-* transformers             4.32.1
 * datasets                 2.14.4
 
-The documentation says to install from source, but sometimes that causes errors.  
+The official documentation says to install from source, but sometimes that causes errors.  
 If you can't get it to work, it might be better to wait until the stable version comes out.  
 Good luck!  
 
@@ -31,7 +43,7 @@ Good luck!
 - finetune.py gptq finetune sample file.
 - jawiki3.csv sample data.(Japanese)
 - lora_test.py after finetune, you can use lora with this script.
-- checkpoint-700 Created sample LoRA
+- checkpoint-700 Created sample LoRA for test.
 
 The model.safetensors is ../gptq_model-4bit-128g.safetensors.  
 It's samefile. I can't find how to change script defaults model name, So I copied it.