Update app.py

app.py

@@ -9,8 +9,11 @@ HAS_GPU = False
 
 # Model title and context size limit
 ctx_limit = 2000
-title = "RWKV-5-World-1B5-v2-20231025-ctx4096"
-model_file = "RWKV-5-World-1B5-v2-20231025-ctx4096"
+#title = "RWKV-5-World-1B5-v2-20231025-ctx4096"
+#model_file = "RWKV-5-World-1B5-v2-20231025-ctx4096"
+
+title = "RWKV-4-World"
+model_file = "RWKV-4-World-7B-v1-20230626-ctx4096"
 
 # Get the GPU count
 try:
@@ -42,23 +45,34 @@ from rwkv.utils import PIPELINE, PIPELINE_ARGS
 pipeline = PIPELINE(model, "rwkv_vocab_v20230424")
 
 # Prompt generation
-def generate_prompt(instruction, input=""):
-    instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n')
-    input = input.strip().replace('\r\n','\n').replace('\n\n','\n')
-    if input:
-        return f"""Instruction: {instruction}
+#def generate_prompt(instruction, input=""):
+    #instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n')
+    #input = input.strip().replace('\r\n','\n').replace('\n\n','\n')
+    #if input:
+        #return f"""Instruction: {instruction}
 
-Input: {input}
+#Input: {input}
 
-Response:"""
-    else:
-        return f"""User: hi
+#Response:"""
+    #else:
+        #return f"""User: hi
 
-Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
+#Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
 
-User: {instruction}
+#User: {instruction}
 
-Assistant:"""
+#Assistant:"""
+
+def generate_prompt(instruction, input=None):
+    instruction = instruction.strip().replace('\r\n','\n').replace('\n\n','\n').replace('\n\n','\n')
+    input = input.strip().replace('\r\n','\n').replace('\n\n','\n').replace('\n\n','\n')
+    if input:
+        return f"""Instruction: {instruction}
+Input: {input}
+Response:"""
+    else:
+        return f"""Question: {instruction}
+Answer:"""
 
 # Evaluation logic
 def evaluate(
@@ -147,7 +161,11 @@ with gr.Blocks(title=title) as demo:
         gr.Markdown(f"This is [RWKV-5 World v2](https://huggingface.co/BlinkDL/rwkv-5-world) with 1.5B params - a 100% attention-free RNN [RWKV-LM](https://github.com/BlinkDL/RWKV-LM). Supports all 100+ world languages and code. And we have [200+ Github RWKV projects](https://github.com/search?o=desc&p=1&q=rwkv&s=updated&type=Repositories). *** Please try examples first (bottom of page) *** (edit them to use your question). Demo limited to ctxlen {ctx_limit}.")
         with gr.Row():
             with gr.Column():
-                prompt = gr.Textbox(lines=2, label="Prompt", value="Assistant: Sure! Here is a very detailed plan to create flying pigs:")
+                #prompt = gr.Textbox(lines=2, label="Prompt", value="Assistant: Sure! Here is a very detailed plan to create flying pigs:")
+
+                instruction = gr.Textbox(lines=2, label="Instruction", value='東京で訪れるべき素晴らしい場所とその紹介をいくつか挙げてください。')
+                input = gr.Textbox(lines=2, label="Input", placeholder="none")
+                
                 token_count = gr.Slider(10, 333, label="Max Tokens", step=10, value=333)
                 temperature = gr.Slider(0.2, 2.0, label="Temperature", step=0.1, value=1.0)
                 top_p = gr.Slider(0.0, 1.0, label="Top P", step=0.05, value=0.3)