update readme and re-train

README.md

@@ -107,6 +107,47 @@ print(result)
 [{'generated_text': 'Given the question:\n{ siapa kamu? }\n---\nAnswer:\nSaya Karina, asisten virtual siap membantu seputar estimasi harga atau pertanyaan lain'}]
 ```
 
+### Infer in Local with Gradio 
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import pipeline
+import re
+
+import gradio as gr
+
+MODEL_NAME = "yodi/karina"
+
+model_4bit = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map="cuda:1", load_in_4bit=True)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+
+prompt = f"Given the question:\n{{ siapa kamu? }}\n---\nAnswer:\n"
+
+generator = pipeline('text-generation',
+                     model=model_4bit,
+                     tokenizer=tokenizer,
+                     do_sample=False)
+
+def preprocess(text):
+    return f"Given the question:\n{{ {text} }}\n---\nAnswer:\n"
+
+def generate(text):
+    preprocess_result = preprocess(text)
+    result = generator(preprocess_result, max_length=256)
+    output = re.split(r'\Given the question:|Answer:|Answer #|Title:',result[0]['generated_text'])[2]
+
+    return output
+
+with gr.Blocks() as demo:
+    input_text = gr.Textbox(label="Input", lines=1)
+    button = gr.Button("Submit")
+    output_text = gr.Textbox(lines=6, label="Output")
+    button.click(generate, inputs=[input_text], outputs=output_text)
+
+demo.launch(enable_queue=True, debug=True)
+```
+And open the gradio url from browser.
+
 ## Training procedure
 
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0314bfcc540631bfb41ef609b0a60e0ce60cc15d8d06e984838ff56967f461de
+oid sha256:9396aa5934350d8ae5a95c7d043a7e3d3396e4b8eaf8301b8cda55929faad2d4
 size 6005240157