Update README.md
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ Please follow the license of the original model.
|
|
20 |
|
21 |
To serve using vLLM with 8x 80GB GPUs, use the following command:
|
22 |
```sh
|
23 |
-
VLLM_WORKER_MULTIPROC_METHOD=spawn python -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --port 12345 --max-model-len 65536 --max-num-batched-tokens 65536 --trust-remote-code --tensor-parallel-size 8 --gpu-memory-utilization 0.97 --dtype
|
24 |
```
|
25 |
You can download the wheel built by [cognitivecomputations](https://huggingface.co/cognitivecomputations) for PyTorch 2.6 and Python 3.12 by clicking [here](https://huggingface.co/x2ray/wheels/resolve/main/vllm-0.7.3.dev187%2Bg0ff1a4df.d20220101.cu126-cp312-cp312-linux_x86_64.whl).
|
26 |
|
@@ -35,9 +35,9 @@ data = {
|
|
35 |
"messages": [
|
36 |
{"role": "user", "content": prompt}
|
37 |
],
|
38 |
-
"max_tokens": 4096,
|
39 |
-
"top_p": 0.9,
|
40 |
-
"temperature": 0.6
|
41 |
}
|
42 |
|
43 |
response = requests.post(url, json=data, headers=headers)
|
@@ -45,151 +45,115 @@ print(response.json()["choices"][0]["message"]["content"])
|
|
45 |
|
46 |
"""
|
47 |
prompt: 一个汉字具有左右结构,左边是木,右边是乞,这个字是什么字,只需要回答这个字即可。
|
48 |
-
|
49 |
<think>
|
50 |
-
|
51 |
-
|
52 |
-
首先,我回忆一下常见的以“木”为偏旁的字,比如“林”、“松”、“柏”等等,但右边是“乞”的可能不太常见。接下来,我可以考虑拆解右边的“乞”字,看看有没有可能和其他偏旁组合成另一个字。
|
53 |
-
|
54 |
-
“乞”这个部首通常读作qǐ,比如“吃”、“迄”等字。左边是“木”,右边是“乞”,可能的结构是左右结构,左边是木字旁,右边是“乞”。那么这样的组合是否存在呢?
|
55 |
|
56 |
-
|
57 |
-
|
58 |
|
59 |
-
|
60 |
-
|
61 |
|
62 |
-
|
|
|
63 |
|
64 |
-
|
|
|
65 |
|
66 |
-
|
67 |
-
|
68 |
-
不过也有可能这个字并不常用,或者属于异体字,所以需要确认正确的答案。根据一些资料,"杚"确实存在,但可能比较生僻,通常在现代汉语中很少使用。因此,正确的答案应该是“杚”字。
|
69 |
</think>
|
70 |
|
71 |
杚
|
72 |
-
--------------------------------------------------
|
73 |
-
|
74 |
-
prompt: 请用我给你的4个数字,通过加、减、乘、除、括号,组成一个运算,使得结果为24。注意:数字需要全部使用我提供的数字,4468
|
75 |
-
|
76 |
-
<think> 嗯,用户给了我四个数字,4、4、6、8,需要组合起来用加减乘除和括号得到24。首先,我得回忆一下24点游戏的常见方法,通常可能需要用到乘法或者除法来增大或减小数值。用户可能已经尝试过
|
77 |
-
一些组合但没成功,所以需要仔细分析。
|
78 |
-
首先,这四个数字中有两个4,一个6和一个8。重复的数字可能会带来不同的组合方式。让我先考虑可能的乘法组合,因为24的因数比较多,比如4×6=24,3×8=24,或者12×2=24。但这里没有3,但可能
|
79 |
-
有其他组合方式。
|
80 |
-
|
81 |
-
比如,如果能用8×3的话,但怎么得到3呢?或者用6×4=24,但剩下的4和8需要处理。可能需要将剩下的数字通过运算抵消掉,比如加减。例如,如果有一个4×6=24,剩下的4和8可能需要组合成0或者1
|
82 |
-
,但这样可能不太行。
|
83 |
-
|
84 |
-
另一个思路是用减法或除法。比如,8/(某个数)得到3,然后乘以剩下的数。比如,8/( (6-4)/4 ),这样算的话,6-4=2,2/4=0.5,8/0.5=16,不够。或者反过来,可能的话。
|
85 |
-
|
86 |
-
或者考虑用括号改变运算顺序。比如,4 × (6 - (8 / 4)),这里8/4=2,6-2=4,4×4=16,还是不够。
|
87 |
-
|
88 |
-
再试试其他组合,比如4×4=16,然后6+8=14,16+14=30,也不对。或者8-6=2,4×4=16,16×2=32,也不对。
|
89 |
-
|
90 |
-
或者考虑用分数,比如8 × (4 - (6/4)),这里6/4=1.5,4-1.5=2.5,8×2.5=20,还是不够。
|
91 |
|
92 |
-
|
93 |
-
|
94 |
-
或者,4 + 4 + 6 + 8=22,接近但不够。
|
95 |
-
|
96 |
-
可能需要用到除法来调整。比如,6 × (8 / (4 / 4)),这里4/4=1,8/1=8,6×8=48,不对。
|
97 |
-
|
98 |
-
或者,8 × 6 × (4 / 4) =48,还是不对。
|
99 |
|
100 |
-
|
101 |
|
102 |
-
|
|
|
|
|
103 |
|
104 |
-
|
|
|
105 |
|
106 |
-
|
|
|
107 |
|
108 |
-
|
109 |
|
110 |
-
|
111 |
|
112 |
-
|
|
|
113 |
|
114 |
-
|
|
|
115 |
|
116 |
-
|
|
|
117 |
|
118 |
-
|
119 |
|
120 |
-
|
121 |
|
122 |
-
|
123 |
-
ng=2。那如何得到2?可能用6-4=2,但这样的话,分母是4 - (4/(6-4))=4 - (4/2)=4-2=2,所以整个式子是8×6/(4 - (4/(6-4)))=48/2=24。这样是否可行?
|
124 |
|
125 |
-
|
126 |
-
4))))
|
127 |
|
128 |
-
|
129 |
|
130 |
-
|
|
|
131 |
|
132 |
-
|
133 |
</think>
|
134 |
|
135 |
-
|
136 |
|
137 |
-
|
138 |
-
|
139 |
-
\]
|
140 |
|
141 |
-
|
142 |
-
1.
|
143 |
-
2.
|
144 |
-
3.
|
145 |
-
4. 分子为 \(8 \times 6 = 48\);
|
146 |
-
5. 最后 \(48 \div 2 = 24\)。
|
147 |
|
148 |
-
|
|
|
149 |
|
150 |
--------------------------------------------------
|
151 |
|
152 |
prompt: How many e in word deepseek?
|
153 |
<think>
|
154 |
-
Okay,
|
155 |
-
|
156 |
-
First, I need to make sure I spell the word correctly. The word is "deepseek". Let me write it out: D-E-E-P-S-E-E-K. Now, I'll go through each letter one by one and count the number of "e"s.
|
157 |
|
158 |
-
Starting with the first letter: D. That's not an E.
|
159 |
|
160 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
161 |
|
162 |
-
|
163 |
-
|
164 |
-
1. D
|
165 |
-
2. E
|
166 |
-
3. E
|
167 |
-
4. P
|
168 |
-
5. S
|
169 |
-
6. E
|
170 |
-
7. E
|
171 |
-
8. K
|
172 |
-
|
173 |
-
Yep, positions 2, 3, 6, 7 are E's. So that's four E's in total. Hmm, but wait, the word "deepseek" has two E's at the beginning, then after P and S, two more E's. So that's 2 + 2 = 4. I think that's correct.
|
174 |
-
|
175 |
-
Alternatively, maybe I can write the word out and underline each E: D E E P S E E K. Each underlined E is a count. Let's count them: 1, 2, 3, 4. Yes, four times.
|
176 |
-
|
177 |
-
I don't think there are any other E's. The user might be confused if they think the last letter is E, but it's K. So the answer should be 4.
|
178 |
</think>
|
179 |
|
180 |
-
The word "deepseek" contains the letter
|
181 |
-
|
182 |
-
1. D
|
183 |
-
2. **E**
|
184 |
-
3. **E**
|
185 |
-
4. P
|
186 |
-
5. S
|
187 |
-
6. **E**
|
188 |
-
7. **E**
|
189 |
-
8. K
|
190 |
|
191 |
-
**
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
192 |
|
|
|
193 |
"""
|
194 |
~~~
|
195 |
|
|
|
20 |
|
21 |
To serve using vLLM with 8x 80GB GPUs, use the following command:
|
22 |
```sh
|
23 |
+
VLLM_WORKER_MULTIPROC_METHOD=spawn python -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --port 12345 --max-model-len 65536 --max-num-batched-tokens 65536 --trust-remote-code --tensor-parallel-size 8 --gpu-memory-utilization 0.97 --dtype float16 --served-model-name deepseek-reasoner --model OPEA/DeepSeek-R1-int4-asym-AutoRound-awq
|
24 |
```
|
25 |
You can download the wheel built by [cognitivecomputations](https://huggingface.co/cognitivecomputations) for PyTorch 2.6 and Python 3.12 by clicking [here](https://huggingface.co/x2ray/wheels/resolve/main/vllm-0.7.3.dev187%2Bg0ff1a4df.d20220101.cu126-cp312-cp312-linux_x86_64.whl).
|
26 |
|
|
|
35 |
"messages": [
|
36 |
{"role": "user", "content": prompt}
|
37 |
],
|
38 |
+
"max_tokens": 4096, # change this to align with offical usage
|
39 |
+
"top_p": 0.9, # change this to align with offical usage
|
40 |
+
"temperature": 0.6 # change this to align with offical usage
|
41 |
}
|
42 |
|
43 |
response = requests.post(url, json=data, headers=headers)
|
|
|
45 |
|
46 |
"""
|
47 |
prompt: 一个汉字具有左右结构,左边是木,右边是乞,这个字是什么字,只需要回答这个字即可。
|
|
|
48 |
<think>
|
49 |
+
嗯,用户问的是一个左右结构的汉字,左边是“木”,右边是“乞”。我需要先确定这个字到底是什么。首先,我应该回忆一下常见的左右结构的汉字,左边是木字旁的字有很多,比如“林”、“松”、“柏”
|
50 |
+
等,但右边是“乞”的可能比较少见。
|
|
|
|
|
|
|
51 |
|
52 |
+
首先,我可以考虑“木”加“乞”组合起来的可能性。可能这个字不是常用字,或者是某个生僻字。我需要检查一下自己的记忆,有没有学过或者见过这样的字。比如,“杞”字是木字旁右边一个“己”,所
|
53 |
+
右边是“己”而不是“乞”。而“札”字右边是“乚”,所以也不是。再比如“杚”,这个字可能比较少见,但它的右边是“乞”吗?
|
54 |
|
55 |
+
或者,可能用户写错了右边的部分,比如“气”而不是“乞”,但用户明确说是“乞”。这时候可能需要查证一下。如果右边确实是“乞”,那么可能的字是“杚”。这个字的读音是什么呢?我记得“杚”有两种
|
56 |
+
音,一种是gài,另一种是gè。当读gài时,同“槩”,也就是“概”的异体字,意思是量米粟时刮平斗斛用的木板;而读gè时,可能与“柯”有关,但不太确定。
|
57 |
|
58 |
+
不过,也有可能用户记错了结构,或者有其他可能性。比如,是否有其他木字旁加乞的字?或者是否是繁体字或异体字?比如“櫂”是木字旁右边比较复杂,但右边不是“乞”。再比如“栔”,右边是“契”
|
59 |
+
上半部分,但也不是“乞”。
|
60 |
|
61 |
+
再仔细想想,可能这个字是“杚”,也就是木字旁加乞,读音为gài或gè。不过,这个字在现代汉语中可能不常用,属于生僻字。需要确认一下是否正确。另外,用户可能是在某个特定的上下文或方言中
|
62 |
+
到这个字,所以需要给出正确的答案。
|
63 |
|
64 |
+
总结一下,可能的答案是“杚”,但需要确认是否正确。如果用户确认结构无误,那么这个字就是“杚”,尽管它不常见。所以最终的答案应该是“杚”。
|
|
|
|
|
65 |
</think>
|
66 |
|
67 |
杚
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
|
69 |
+
--------------------------------------------------
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
|
71 |
+
prompt="请用我给你的4个数字,通过加、减、乘、除、括号,组成一个运算,使得结果为24。注意:数字需要全部使用我提供的数字,4468"
|
72 |
|
73 |
+
<think>
|
74 |
+
嗯,我现在需要解决一个数学问题,就是用给定的四个数字4、4、6、8,通过加减乘除和括号组合起来得到24。首先,我得仔细想清楚怎么安排这些数字和运算符号。可能的话,先回忆一下常见的24
|
75 |
+
点游戏解法,可能会有帮助。
|
76 |
|
77 |
+
首先,我需要确定这四个数字的顺序和组合方式。因为有重复的数字,比如有两个4,所以可能需要更多的组合尝试。先考虑如何用这四个数中的某些数相乘或相除得到较大的数值,然后再调整剩下的
|
78 |
+
数来达到24。
|
79 |
|
80 |
+
比如,8和6这两个比较大的数,可能相乘的话是48,这样的话,剩下的两个4可能需要调整到48的一半,即24。不过这里有两个4,所以可能需要用除法或者减法。比如,48减去(4+4)=40,这样就不
|
81 |
+
行。或者48除以(4/4)=48,也不对。或者用8*6=48,然后4-4=0,这样48+0=48,也不行。
|
82 |
|
83 |
+
再想另一个方向,比如用4和4相乘得到16,再加上6和8的话,16+6+8=30,超过了24。或者16*(8-6)=32,也不对。或者(4*4)+6+8= 16+14=30,还是太大。
|
84 |
|
85 |
+
或者考虑用减法,比如8*4=32,然后32减去(6+4)=32-10=22,也不够。或者32-6-4=22,同样不行。
|
86 |
|
87 |
+
可能需要用除法来调整数值。比如,8除以(6-4)=4,这样再乘以剩下的4和另一个数?不过这样的话,可能不够。比如8/(6-4)=4,然后4*4=16,再加上6的话就超过了,不过这里可能重复用了6?或
|
88 |
+
者可能没正确使用所有数字。
|
89 |
|
90 |
+
再考虑另一种组合,比如(8-6)=2,然后4*4=16,再16*2=32,还是不行。或者(4+8)*(6-4)=12*2=24,这样用了4、8、6、4四个数字吗?是的,4+8=12,6-4=2,12*2=24,这样的话,确实用到了
|
91 |
+
所有的四个数字:4、8、6、4。所以这个组合可能可行?
|
92 |
|
93 |
+
不过,让我再检查一遍:4+8=12,6-4=2,然后12乘2等于24。是的,这样的话,四个数字都用到了,对吗?第一个4,第二个8,第三个6,第四个4。是的,刚好是4、4、6、8。所以这个解法是可行的
|
94 |
+
。
|
95 |
|
96 |
+
不过可能还有其他解法。比如,用6乘以(8 - (4/4))。计算一下:4/4=1,8-1=7,6*7=42,不对。或者(6*8)/(4/4)=48/1=48,也不对。
|
97 |
|
98 |
+
或者(4*6)*(8/4)=24*2=48,同样不行。或者(4*8)-(6-4)=32-2=30,还是不行。
|
99 |
|
100 |
+
再试试其他组合,比如4*(6+8)/4。这里,6+8=14,4*14=56,56/4=14,不对。
|
|
|
101 |
|
102 |
+
或者,8*(6 - (4/4)):4/4=1,6-1=5,8*5=40,也不对。
|
|
|
103 |
|
104 |
+
或者,4*4*(8-6)=16*2=32,还是不够。
|
105 |
|
106 |
+
不过之前的那个解法(4+8)*(6-4)=12*2=24,确实可行。因此,这可能是一个正确的答案。不过需要确认是否所有的数字都被使用了一次,并且每个数字都只用了一次。这里,4被用了两次,而题目
|
107 |
+
中给出的数字是两个4,所以没问题。是的,正确使用了所有四个数字:4、4、6、8,每个数字都用了一次,没有重复使用也没有遗漏。
|
108 |
|
109 |
+
所以最终的表达式是(4 + 8)× (6 - 4) = 24。
|
110 |
</think>
|
111 |
|
112 |
+
使用数字4、4、6、8,可以通过以下运算得到24:
|
113 |
|
114 |
+
**运算步骤**:
|
115 |
+
(4 + 8) × (6 - 4) = 12 × 2 = 24
|
|
|
116 |
|
117 |
+
**验证**:
|
118 |
+
1. 使用所有数字:4、4、6、8(两个4均被使用)。
|
119 |
+
2. 通过加法和减法组合,最终结果为24。
|
120 |
+
3. 符合题目要求,仅使用加、减、乘、除和括号。
|
|
|
|
|
121 |
|
122 |
+
**答案**:
|
123 |
+
(4 + 8) × (6 - 4) = 24
|
124 |
|
125 |
--------------------------------------------------
|
126 |
|
127 |
prompt: How many e in word deepseek?
|
128 |
<think>
|
129 |
+
Okay, let's see. The question is asking how many times the letter "e" appears in the word "deepseek." Alright, first, I need to make sure I spell the word correctly. D-E-E-P-S-E-E-K. Let me break it down letter by letter.
|
|
|
|
|
130 |
|
131 |
+
Starting with the first letter: D. That's a D, not an E. Second letter: E. That's one. Third letter: E again. That's two. Fourth letter: P. Then S. Next is E. That's the third E. Then another E. Wait, let me check again. D-E-E-P-S-E-E-K. So after S, there's E, E, K. So that's E as the fifth letter, sixth letter, and then K. Wait, let me count the positions again to be sure.
|
132 |
|
133 |
+
1: D
|
134 |
+
2: E
|
135 |
+
3: E
|
136 |
+
4: P
|
137 |
+
5: S
|
138 |
+
6: E
|
139 |
+
7: E
|
140 |
+
8: K
|
141 |
|
142 |
+
So positions 2, 3, 6, 7 are E's. That makes four E's in total. Let me verify by writing the word out and underlining each E: D E E P S E E K. Yes, that's four E's. Wait, but sometimes people might miscount, especially if letters are repeated in sequence. Let me check again. The word is "deepseek." So "deep" has two E's, then "seek" has two E's as well. So deep (D-E-E-P) and seek (S-E-E-K). So 2 + 2 = 4. That makes sense. I think that's right. No, wait, "seek" is S-E-E-K, so two E's. So total of four E's. Yeah, that seems correct. I don't think I missed any. Let me write it again: D, E, E, P, S, E, E, K. Yep, four E's. So the answer should be 4.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
</think>
|
144 |
|
145 |
+
The word "deepseek" contains the letter "e" four times. Here's the breakdown:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
146 |
|
147 |
+
1. **D** - Not an "e"
|
148 |
+
2. **E** - First "e"
|
149 |
+
3. **E** - Second "e"
|
150 |
+
4. **P** - Not an "e"
|
151 |
+
5. **S** - Not an "e"
|
152 |
+
6. **E** - Third "e"
|
153 |
+
7. **E** - Fourth "e"
|
154 |
+
8. **K** - Not an "e"
|
155 |
|
156 |
+
**Answer:** There are **4** instances of the letter "e" in "deepseek".
|
157 |
"""
|
158 |
~~~
|
159 |
|