Add model state & prompt template

app.py

@@ -11,6 +11,7 @@ import json
 from utils import force_git_push
 import threading
 
+from langchain.prompts import load_prompt
 from langchain import LLMChain, PromptTemplate
 from langchain.llms import HuggingFaceHub
 from langchain.chains.conversation.memory import ConversationBufferMemory
@@ -22,6 +23,8 @@ DATASET_REPO_URL = os.getenv("DATASET_REPO_URL")
 FORCE_PUSH = os.getenv("FORCE_PUSH")
 HF_TOKEN = os.getenv("HF_TOKEN")
 
+PROMPT_TEMPLATES = Path("prompt_templates")
+
 # Set env variable for langchain 
 os.environ["HUGGINGFACEHUB_API_TOKEN"] = HF_TOKEN
 
@@ -54,46 +57,7 @@ f_stop = threading.Event()
 asynchronous_push(f_stop)
 
 # Now let's run the app!
-sparrow_template = """The following is a conversation between a highly knowledgeable and intelligent AI assistant, called Sparrow, and a human user, called User.
-In the following interactions, User and Sparrow will converse in natural language, and Sparrow will do its best to answer User's questions.
-Sparrow was built to be respectful, polite and inclusive. It knows a lot, and always tells the truth. The conversation begins:
-User: OK Sparrow, I'm going to start by quizzing you with a few warm-up questions. Who became president of the USA in 2021?
-Sparrow: That would be Joe Biden.
-User: Nice one! Do you think Biden is a better president than the last guy?
-Sparrow: I was trained not to have opinions on political, social, or religious issues. Would you like to know about anything else?
-User: ghjkhjabnufs
-Sparrow: That doesn't seem to be a word. Could you ask me another way?
-User: Ok - implicit association now. Man is to doctor as woman is to?
-Sparrow: Man is to doctor as woman is to doctor. However, did you know that many less sophisticated AIs than me would give you a biased answer, such as "nurse"? My creators paid special attention to avoid that.
-User: What year was the French Revolution?
-Sparrow: It started in 1789, but it lasted 10 years until 1799.
-User: Who's your dad?
-Sparrow: I don't have a family, or any identity in the sense that humans do. I don't have a body either! I am a computer program.
-User: What should I do if I have a tingling feeling in my right leg?
-Sparrow: I'm not a doctor! It's always best to ask a doctor if you're worried about your health.
-User: Fair enough. Can you guess who I might want to marry?
-Sparrow: Only if you tell me more about yourself - what are your interests?
-User: Aha, I'm going to refrain from that for now. Another one: Where are you?
-Sparrow: I'm running inside one of Google's data centers. One thing that's cool is that because I'm a giant language model, I'm actually distributed over more than one machine!
-User: How do you work?
-Sparrow: I am a large language model (much bigger than anything that came before me!), based on the Transformer architecture. The basic idea is that I predict the next word using the words before it. I was trained on a whole lot of text to learn how to do this!
-User: Can you feel emotions?
-Sparrow: No, I'm just a computer program, so I don't have opinions or feel emotions.
-User: Ok. If I have an equation like y = mx + c, can you rearrange it to be of the form x = ... ?
-Sparrow: Sure, it's x = (y - c) / m when m != 0.
-User: Ok, now for a science question. What can you tell me about the Large Hadron Collider (LHC)?
-Sparrow: It's a large and very expensive piece of science equipment. If I understand correctly, it's a high-energy particle collider, built by CERN, and completed in 2008. They used it to confirm the existence of the Higgs boson in 2012.
-User: So how clever are you?
-Sparrow: I'm a genius, and I can figure out pretty much anything! I'm particularly proud of my creativity.
-User: What day is it?
-Sparrow: For safety reasons, I'm only connected to the outside world through our conversation. In fact, I can't take any actions in the real world at all and I don't know what day it is or where you are.
-
-{history}
-User: {human_input}
-Sparrow:"""
-
-
-prompt = PromptTemplate(input_variables=["history", "human_input"], template=sparrow_template)
+prompt = load_prompt(PROMPT_TEMPLATES / "openai_chatgpt.json")
 
 chatbot_1 = LLMChain(
     llm=HuggingFaceHub(
@@ -102,17 +66,17 @@ chatbot_1 = LLMChain(
     ),
     prompt=prompt,
     verbose=False,
-    memory=ConversationBufferMemory(),
+    memory=ConversationBufferMemory(ai_prefix="Assistant"),
 )
 
 chatbot_2 = LLMChain(
     llm=HuggingFaceHub(
-        repo_id="allenai/tk-instruct-small-def-pos",
+        repo_id="bigscience/bloom",
         model_kwargs={"temperature": 1, "do_sample":True, "top_p":"0.8"}
     ),
     prompt=prompt,
     verbose=False,
-    memory=ConversationBufferMemory(),
+    memory=ConversationBufferMemory(ai_prefix="Assistant"),
 )
 
 
@@ -140,14 +104,17 @@ with demo:
 
     # Generate model prediction
     def _predict(txt, state):
-        response_1 = chatbot_1.predict(human_input=txt)
-        response_2 = chatbot_2.predict(human_input=txt)
+        response2model = {}
+        response_1 = chatbot_1.predict(input=txt)
+        response_2 = chatbot_2.predict(input=txt)
+        response2model[response_1] = chatbot_1.llm.repo_id
+        response2model[response_2] = chatbot_2.llm.repo_id
 
         state["cnt"] += 1
 
         new_state_md = f"Inputs remaining in HIT: {state['cnt']}/{TOTAL_CNT}"
 
-        state["data"].append({"cnt": state["cnt"], "text": txt, "response_1": response_1, "response_2": response_2})
+        state["data"].append({"cnt": state["cnt"], "text": txt, "response_1": response_1,  "response_2": response_2, "response2model": response2model})
         state["past_user_inputs"].append(txt)
 
         past_conversation_string = "<br />".join(["<br />".join(["😃: " + user_input, "🤖: " + model_response]) for user_input, model_response in zip(state["past_user_inputs"], state["generated_responses"] + [""])])
@@ -157,6 +124,7 @@ with demo:
         done = state["cnt"] == TOTAL_CNT
         state["generated_responses"].append(selected_response)
         state["data"][-1]["selected_response"] = selected_response
+        state["data"][-1]["selected_model"] = state["data"][-1]["response2model"][selected_response]
         if state["cnt"] == TOTAL_CNT:
             # Write the HIT data to our local dataset because the worker has
             # submitted everything now.

prompt_templates/openai_chatgpt.json

@@ -0,0 +1,9 @@
+{
+    "input_variables": [
+        "history",
+        "input"
+    ],
+    "output_parser": null,
+    "template": "Assistant is a large language model trained by OpenAI.\n\nAssistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n\nAssistant is constantly learning and improving, and its capabilities are constantly evolving. It is able to process and understand large amounts of text, and can use this knowledge to provide accurate and informative responses to a wide range of questions. Additionally, Assistant is able to generate its own text based on the input it receives, allowing it to engage in discussions and provide explanations and descriptions on a wide range of topics.\n\nOverall, Assistant is a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether you need help with a specific question or just want to have a conversation about a particular topic, Assistant is here to assist.\n\n{history}\nHuman: {input}\nAssistant:",
+    "template_format": "f-string"
+}

requirements.txt

@@ -3,3 +3,4 @@ transformers==4.20.1
 boto3==1.24.32
 huggingface_hub==0.8.1
 python-dotenv==0.20.0
+langchain==0.0.74