Update README.md
Browse files
README.md
CHANGED
|
@@ -34,7 +34,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
| 34 |
|
| 35 |
instruction = "Please reason step by step, and put your final answer within \\boxed{}."
|
| 36 |
prompt = "The arithmetic mean of 7, 2, $x$ and 10 is 9. What is the value of $x$?"
|
| 37 |
-
#
|
| 38 |
# prompt = "How many r's are in the word \"strawberry\""
|
| 39 |
|
| 40 |
messages = [
|
|
@@ -51,7 +51,10 @@ model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
|
| 51 |
|
| 52 |
generated_ids = model.generate(
|
| 53 |
**model_inputs,
|
| 54 |
-
max_new_tokens=16384
|
|
|
|
|
|
|
|
|
|
| 55 |
)
|
| 56 |
generated_ids = [
|
| 57 |
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
|
@@ -67,6 +70,56 @@ print(f"\nThink Mode: {think_mode}")
|
|
| 67 |
print(f"Number of tokens: {num_tokens}")
|
| 68 |
```
|
| 69 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
|
| 71 |
## Citation
|
| 72 |
If you find this work helpful, please cite:
|
|
|
|
| 34 |
|
| 35 |
instruction = "Please reason step by step, and put your final answer within \\boxed{}."
|
| 36 |
prompt = "The arithmetic mean of 7, 2, $x$ and 10 is 9. What is the value of $x$?"
|
| 37 |
+
#prompt = "What is the smallest positive perfect cube that can be written as the sum of three consecutive integers?"
|
| 38 |
# prompt = "How many r's are in the word \"strawberry\""
|
| 39 |
|
| 40 |
messages = [
|
|
|
|
| 51 |
|
| 52 |
generated_ids = model.generate(
|
| 53 |
**model_inputs,
|
| 54 |
+
max_new_tokens=16384,
|
| 55 |
+
do_sample=True,
|
| 56 |
+
temperature=0.6,
|
| 57 |
+
top_p=0.95
|
| 58 |
)
|
| 59 |
generated_ids = [
|
| 60 |
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
|
|
|
| 70 |
print(f"Number of tokens: {num_tokens}")
|
| 71 |
```
|
| 72 |
|
| 73 |
+
## Case Study
|
| 74 |
+
|
| 75 |
+
**User:**
|
| 76 |
+
```
|
| 77 |
+
1+1=?
|
| 78 |
+
```
|
| 79 |
+
|
| 80 |
+
**Thinkless-1.5B:**
|
| 81 |
+
```
|
| 82 |
+
<short>
|
| 83 |
+
To solve the problem \(1 + 1\), we will follow a step-by-step approach:
|
| 84 |
+
|
| 85 |
+
1. **Identify the numbers involved**: We have the numbers 1 and 1.
|
| 86 |
+
2. **Understand the operation**: The operation we need to perform is addition.
|
| 87 |
+
3. **Perform the addition**: When we add 1 and 1 together, we get 2.
|
| 88 |
+
|
| 89 |
+
So, the final answer is \(\boxed{2}\).
|
| 90 |
+
```
|
| 91 |
+
|
| 92 |
+
**DeepSeek-R1:**
|
| 93 |
+
```
|
| 94 |
+
Okay, so I need to figure out what 1 plus 1 equals. Let me start by thinking about basic addition. When you add two numbers together, you're combining their values. So if I have one apple and someone gives me another apple, how many apples do I have in total? That should be two apples.
|
| 95 |
+
|
| 96 |
+
Wait, let me make sure I'm not missing something here. In the simplest terms, addition is taking two quantities and putting them together. So 1 plus 1 means combining a single unit with another single unit. If I use my fingers, holding up one finger on my left hand and one on my right, then when I put them together, I have two fingers up. That seems right.
|
| 97 |
+
|
| 98 |
+
But maybe there's a trick to this question. Sometimes problems that look easy might have a different answer depending on the context. For example, in binary, 1 + 1 equals 10. But the question doesn't specify a number system, so I should assume it's in the decimal system, which is the default. So in decimal, 1 + 1 is definitely 2.
|
| 99 |
+
|
| 100 |
+
Another way to check is by using the number line. Starting at 1, if I move one unit to the right, I land on 2. That confirms it. Or using basic arithmetic rules: the sum of 1 and 1 is the next number in the sequence after 1, which is 2.
|
| 101 |
+
|
| 102 |
+
I guess there's no ambiguity here. Unless the question is trying to be philosophical or something, but mathematically, it's straightforward. So the answer should be 2.
|
| 103 |
+
|
| 104 |
+
The sum of 1 and 1 is calculated as follows:
|
| 105 |
+
|
| 106 |
+
1 + 1 = 2
|
| 107 |
+
|
| 108 |
+
In decimal arithmetic, adding the numbers 1 and 1 results in the number 2.
|
| 109 |
+
```
|
| 110 |
+
|
| 111 |
+
---
|
| 112 |
+
|
| 113 |
+
**User:**
|
| 114 |
+
```
|
| 115 |
+
Define\n\\[p = \\sum_{k = 1}^\\infty \\frac{1}{k^2} \\quad \\text{and} \\quad q = \\sum_{k = 1}^\\infty \\frac{1}{k^3}.\\] Find a way to write\n\\[\\sum_{j = 1}^\\infty \\sum_{k = 1}^\\infty \\frac{1}{(j + k)^3}\\] in terms of $p$ and $q.
|
| 116 |
+
```
|
| 117 |
+
|
| 118 |
+
**Thinkless-1.5B:**
|
| 119 |
+
```
|
| 120 |
+
|
| 121 |
+
```
|
| 122 |
+
|
| 123 |
|
| 124 |
## Citation
|
| 125 |
If you find this work helpful, please cite:
|