Update README.md

README.md

@@ -8,7 +8,7 @@ license: mit
 ---
 
 
-*Update: Having a bit issue with the tokenizer, still figuring things out.
+**Bug**: Having a bit issue with the tokenizer, still figuring out...You can use the original Yi tokenizer configuratin.
 
 
 Reproduce Vicuna, but based on yi-6B. The training data I used was ShareGPT_V3_unfiltered_cleaned_split_no_imsorry.json. 
@@ -60,6 +60,12 @@ The training used 5*A800 for 3 epochs
   train_steps_per_second   =              0.224
 ```
 
+Post-training inference is also using this repository:
+```
+CUDA_VISIBLE_DEVICES=4 python gradio_demo.py  --model_type auto --base_model /data/mn/shibing624/MedicalGPT-1.6.3-231215/outputs/20240106_yi6B_vicuna    --tokenizer_path /data/mn/shibing624/MedicalGPT-1.6.3-231215/outputs/20240106_yi6B_vicuna --template_name yi --gpus 4
+CUDA_VISIBLE_DEVICES=6 python inference.py --model_type auto --base_model /data/mn/shibing624/MedicalGPT-1.6.3-231215/outputs/20240106_yi6B_vicuna      --template_name yi --gpus 6     --interactive --tokenizer_path /data/llm/models/Pretrained/yi-6B/01ai/Yi-6B
+```
+
 We can see from some preliminary results, the conversation is natural and informative (unsurprisingly).
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6413d7be996b2e426f230fb7/WfQYyyLxtXA2KlePmIPQJ.png)