初始化项目，由ModelHub XC社区提供模型

Model: NotHereNorThere/Coral-v1.5-4b
Source: Original Platform

tests/QnA1.txt

@@ -0,0 +1,50 @@
+Q: 47x83
+A: To multiply 47 by 83, we can break down the multiplication into smaller parts:
+
+First, multiply 47 by 3 (the ones place of 83):
+47 x 3 = 141
+
+Then, multiply 47 by 8 (the tens place of 83):
+47 x 80 = 3760
+
+Now, add the two results together:
+141 + 3760 = 3901
+
+So, 47 x 83 equals 3901.
+
+
+Q: my name is mike // what is my name
+A: Hello, Mike! How can I assist you today? // Your name is Mike.
+
+Q: lsit 3 fruits
+A 1. Apple
+2. Banana
+3. Orange
+
+
+Q: who made you
+A: I was developed by Alibaba Cloud's Tongyi Lab. My name is Qwen.
+
+Q: write a short python script to check if a number is prime
+A: `def is_prime(n):
+    if n <= 1:
+        return False
+    if n == 2:
+        return True
+    if n % 2 == 0:
+        return False
+
+    i = 3
+    while i * i <= n:
+        if n % i == 0:
+            return False
+        i += 2
+
+    return True
+
+# Example usage:
+num = int(input("Enter a number: "))
+if is_prime(num):
+    print(f"{num} is a prime number.")
+else:
+    print(f"{num} is not a prime number.")`

tests/QnA2.txt

@@ -0,0 +1,17 @@
+Q: A train leaves Chicago at 60mph, another leaves NYC at 80mph, they're 800 miles apart, when do they meet?
+A: Let's reason step-by-step:
+1. The train from Chicago is traveling at 60mph, and the train from NYC is traveling at 80mph.
+2. When two objects move towards each other, their speeds are added together. In this case, the combined speed is 60mph + 80mph = 140mph.
+3. They are 800 miles apart when they start, and we want to find out how long it takes for them to cover this distance at their combined speed.
+4. To find the time it takes, we divide the distance by the combined speed: 800 miles / 140mph = approximately 5.71 hours.
+5. Since there are 60 minutes in an hour, we can convert 0.71 hours to minutes: 0.71 * 60 ≈ 42.6 minutes.
+6. So, they will meet after approximately 5 hours and 43 minutes.
+
+Final answer: The trains will meet after approximately 5 hours and 43 minutes.
+
+
+Q: Write a haiku about quantum physics where every line starts with Q
+A: Quantum phenomena
+Quantum entanglement's strange bond,
+Quantum mysteries.
+

tests/conv-test.txt

@@ -0,0 +1,132 @@
+> hi
+
+Hello! How can I assist you today?
+
+[ Prompt: 69.3 t/s | Generation: 76.2 t/s ]
+
+> who are you
+
+I am Qwen, a large-scale language model independently developed by Alibaba Cloud's Tongyi Lab. I support 100 languages, including but not limited to Chinese, English, German, French, Spanish, and many more. I can answer questions, create text such as writing stories, official documents, emails, scripts, perform logical reasoning, code generation, and even express opinions and play games. If you have any questions or need help, please feel free to ask me!
+
+[ Prompt: 1093.4 t/s | Generation: 71.3 t/s ]
+
+> what can you do
+
+I can do the following:
+
+1. Answer questions: I can answer questions on a wide range of topics, from general knowledge to specific details.
+
+2. Create text: I can write stories, official documents, emails, scripts, and more, based on the input you provide.
+
+3. Logical reasoning: I can analyze situations and provide logical conclusions.
+
+4. Programming: I can write code in various programming languages, such as Python, Java, C++, etc.
+
+5. Express opinions: I can express my opinions on various topics, although they are based on the information I've been trained on.
+
+6. Play games: I can engage in text-based games or puzzles with you.
+
+7. Translate languages: Since I support over 100 languages, I can translate text between these languages.
+
+Remember, while I strive to provide accurate and helpful responses, I am an AI and may not have all the information at my disposal. If you have a question or need help with something, please feel free to ask me!
+
+[ Prompt: 676.9 t/s | Generation: 71.5 t/s ]
+
+> how do you work
+
+I work by processing input and generating output based on the data I was trained on. Here's a step-by-step overview of how I work:
+
+1. Input: You provide me with input, which could be a question, statement, instruction, etc.
+
+2. Tokenization: The input is broken down into smaller units, called tokens. These tokens can be words, subwords, or characters.
+
+3. Embedding: Each token is converted into a numerical representation called an embedding. This embedding captures the meaning and context of the token.
+
+4. Processing: The embeddings are then processed through multiple layers of the model. This process involves complex mathematical operations that allow the model to understand the context and meaning of the input.
+
+5. Output: The final output is a sequence of tokens that form a response to your input. This response is then converted back into a human-readable format.
+
+6. Training: The model is trained on a vast amount of text data, which allows it to learn patterns, relationships, and facts. The more data it has, the better it can understand and generate text.
+
+7. Optimization: The model is constantly being optimized and improved through techniques like fine-tuning, transfer learning, and reinforcement learning.
+
+8. Deployment: Once the model is trained and optimized, it can be deployed to provide services like answering questions, creating text, and more.
+
+In summary, I work by taking in input, converting it into numerical representations, processing these representations through multiple layers of the model, and then generating an output based on the processed information. The more data I have and the more I'm trained on, the better I can understand and respond to your queries.
+
+[ Prompt: 660.5 t/s | Generation: 70.1 t/s ]
+
+> tell me a joke
+
+Why don't scientists trust atoms? Because they make up everything!
+
+[ Prompt: 610.8 t/s | Generation: 73.6 t/s ]
+
+> what is the capital of france
+
+The capital of France is Paris.
+
+[ Prompt: 757.7 t/s | Generation: 73.8 t/s ]
+
+> germany?
+
+The capital of Germany is Berlin.
+
+[ Prompt: 980.9 t/s | Generation: 75.1 t/s ]
+
+> tell me another joke
+
+Why don't scientists trust atoms? Because they make up everything!
+
+[ Prompt: 302.3 t/s | Generation: 72.9 t/s ]
+
+> you already said that one
+
+I apologize for the repetition. Here's another one:
+
+Why did the scarecrow win an award? Because he was outstanding in his field!
+
+[ Prompt: 686.0 t/s | Generation: 71.4 t/s ]
+
+> whats 5x12
+
+The product of 5 and 12 is 60.
+
+[ Prompt: 844.9 t/s | Generation: 72.9 t/s ]
+
+> how do you know
+
+I know this because I have been trained on a vast amount of data that includes mathematical concepts and operations. I have been taught to perform calculations like multiplication, addition, subtraction, and division. So, I can determine that 5 multiplied by 12 equals 60.
+
+[ Prompt: 662.0 t/s | Generation: 69.9 t/s ]
+
+> whats your name again?
+
+My name is Qwen, a large-scale language model independently developed by Alibaba Cloud's Tongyi Lab.
+
+[ Prompt: 737.7 t/s | Generation: 70.6 t/s ]
+
+> what was the first joke you told me
+
+The first joke I told you was: "Why don't scientists trust atoms? Because they make up everything!"
+
+[ Prompt: 885.0 t/s | Generation: 70.5 t/s ]
+
+> when did i ask the capital of italy
+
+I don't have access to your conversation history, so I don't know when you asked about the capital of Italy.
+
+[ Prompt: 941.7 t/s | Generation: 70.7 t/s ]
+
+> when did i ask you the capital of italy
+
+I don't have access to your conversation history, so I don't know when you asked about the capital of Italy.
+
+[ Prompt: 1780.8 t/s | Generation: 70.5 t/s ]
+
+> what is it
+
+The capital of Italy is Rome.
+
+[ Prompt: 590.4 t/s | Generation: 75.7 t/s ]
+