Mistral Nemo 12B R1 V0.2
模型概述
該模型在1臺Nvidia H100上進行了12小時的微調,擅長處理需要分步推理的任務,如數學問題解答和邏輯分析。
模型特點
系統性推理能力
採用<think>標籤格式進行結構化思考,提供至少6個邏輯步驟的詳細推理過程
高效微調
僅需12小時H100訓練即可獲得優質推理能力
數學邏輯處理
擅長數值比較、計數等需要逐步驗證的任務
模型能力
分步邏輯推理
數學問題解答
文本生成
結構化思考
使用案例
教育輔助
數學問題解答
解決需要分步驗證的數學比較問題
如示例中準確比較9.9和9.11的大小
邏輯測試
字母計數
執行精確的字母位置分析和計數
如示例中正確識別'strawberry'包含3個R
🚀 Mistral Nemo 12B R1
Mistral Nemo 12B R1 是一個文本生成模型,它基於 Mistral-Nemo-Instruct-2407 進行微調,在特定數據集上訓練後,可用於生成具有推理過程的文本。
🚀 快速開始
本模型在 1 塊英偉達 H100 顯卡上進行了 12 小時 的微調,具體設置如下:
- 批次大小:26
- 梯度累積步數:1
- 訓練輪數:1
- 學習率:2e - 5
- 熱身比例:0.1
運行模型的代碼如下:
import torch
from transformers import pipeline
model_id = "CreitinGameplays/Mistral-Nemo-12B-R1-v0.2"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype=torch.bfloat16,
device_map="auto"
)
messages = [
{"role": "user", "content": "How many r's are in strawberry?"}
]
outputs = pipe(
messages,
max_new_tokens=2048
)
print(outputs[0]["generated_text"][-1])
💻 使用示例
基礎用法
以下是使用該模型生成回覆的示例:
- 用戶輸入:
how many r's are in the word strawberry
- 模型輸出:
<think>
Okay, so the question is asking how many R's are in the word "strawberry." Hmm, let me think about this step by step.
First, I need to write down the word to make it easier to count. So, "strawberry" is the word. Now, I should go through each letter one by one to check for the letter R.
Starting from the beginning, the first letter is S. Then, the second letter is T, the third is R, the fourth is A, the fifth is W, the sixth is B, the seventh is E, the eighth is R, the ninth is R, the tenth is Y. Wait, so I've counted up to the tenth letter, which is Y.
Now, I need to count how many of those are R's. Let's see: the third letter is R, the eighth letter is R, and the ninth letter is R. So that's three R's in total.
Wait, hold on, let me double-check to make sure I didn't miss any. The word is "strawberry." S, T, R, A, W, B, E, R, R, Y. Yeah, that's three R's. So, the answer should be three.
I think that's it. I don't see any other R's in the word. So, the number of R's in "strawberry" is three.
**Final Answer**
The word "strawberry" contains three R's.
</think>
The word "strawberry" contains three R's.
**Answer:** Three R's.</s>
高級用法
- 用戶輸入:
which number has bigger value, 9.9 or 9.11? think step by step.
- 模型輸出:
<think>
Okay, so I have this question here: which number is bigger, 9.9 or 9.11? Hmm, let me think about this step by step. I remember that when we compare numbers, we can look at their whole number parts first. So, both numbers start with 9. That means they are equal in terms of the whole number part, right? So, they are both 9.
Now, since the whole numbers are the same, the next thing to compare would be the decimal parts. The decimal part of 9.9 is 0.9, and for 9.11, it's 0.11. I need to figure out which of these decimal parts is larger.
I recall that when comparing decimals, we can line them up by the place value to make it easier. So, let's write them out:
9.9 is equal to 9.900000...
And 9.11 is equal to 9.110000...
Now, if I line them up by the tenths place, it looks like this:
9.900000...
9.110000...
Looking at the tenths place, the first number has 9 and the second has 1. Since 9 is larger than 1, the first number is bigger. Therefore, 9.9 is larger than 9.11.
Wait, but let me double-check to make sure I didn't make a mistake. Sometimes, when comparing decimals, it's easy to overlook the significance of the place value. So, let me consider the hundredths place as well. In 9.9, the hundredths place is 9, and in 9.11, it's 1. So, again, 9 is larger than 1, which confirms that 9.9 is bigger.
Is there another way to think about this? Maybe by converting them to fractions or something? Let me try that. 9.9 is equal to 9 and 9/10, and 9.11 is equal to 9 and 11/100. So, 9 and 9/10 is larger than 9 and 11/100 because 9/10 is larger than 11/100.
Alternatively, I can express both numbers as fractions with the same denominator to compare them. 9.9 is 99/10, and 9.11 is 911/100. If I find a common denominator, which is 100, then 99/10 is equal to 990/100 and 911/100 is just 911/100. Comparing 990 and 911, 990 is definitely larger than 911, so 9.9 is bigger.
Another way is to think about how many times 0.1 is in each number. 9.9 is 9 and a half, which is 9.5, and 9.11 is 9 and a bit more than half, which is less than 9.5. So, 9.9 is larger.
Wait, but maybe I should consider the context of the question. Is this a math problem or something else? If it's a math problem, then the answer is straightforward. But if it's in a different context, like comparing prices or something, maybe the answer is different? Hmm, but the question is just asking which number is bigger, so I think it's a straightforward math question.
Let me also think about the place value in a different way. The number 9.9 has a 9 in the tenths place, which is more significant than the 1 in the tenths place of 9.11. So, that means 9.9 is larger.
Is there a way to visualize this? Maybe by using a number line. On the number line, 9.9 is to the right of 9.11, so it's larger. That makes sense.
Another thought: if I add 0.1 to both numbers, 9.9 becomes 10, and 9.11 becomes 9.21. Clearly, 10 is larger than 9.21, so 9.9 is bigger. That seems to confirm my earlier conclusion.
Wait, let me try adding 0.01 to both numbers. 9.9 becomes 9.91, and 9.11 becomes 9.12. Now, 9.91 is still larger than 9.12. So, that also shows that 9.9 is bigger.
I think I've considered this from multiple angles, and each time, 9.9 comes out as the larger number. So, I'm confident that 9.9 is bigger than 9.11.
**Final Answer**
The number with the larger value is \boxed{9.9}.
</think>
To determine which number is larger, 9.9 or 9.11, we can follow these steps:
1. **Compare the whole number parts**: Both numbers start with 9, so they are equal in terms of the whole number part.
2. **Compare the decimal parts**: The decimal part of 9.9 is 0.9, and the decimal part of 9.11 is 0.11. We need to compare these two decimals.
3. **Line up the decimals by place value**:
- 9.9 is equal to 9.900000...
- 9.11 is equal to 9.110000...
4. **Compare the tenths place**: The first number has 9 and the second has 1. Since 9 is larger than 1, the first number is bigger.
5. **Compare the hundredths place**: The first number has 9 and the second has 1. Again, 9 is larger than 1, confirming that the first number is bigger.
6. **Convert to fractions for verification**:
- 9.9 is equal to 99/10.
- 9.11 is equal to 911/100.
- Comparing 99/10 and 911/100, we find that 99/10 is larger than 911/100.
7. **Consider the number line**: On the number line, 9.9 is to the right of 9.11, indicating that it is larger.
8. **Add small numbers to both**:
- Adding 0.1 to both: 9.9 becomes 10, and 9.11 becomes 9.21. Clearly, 10 is larger.
- Adding 0.01 to both: 9.9 becomes 9.91, and 9.11 becomes 9.12. Again, 9.91 is larger.
All methods lead to the conclusion that 9.9 is larger than 9.11.
\[
\boxed{9.9}
\]</s>
📚 詳細文檔
激活推理步驟的推薦系統提示如下:
You are an AI focused on providing systematic, well-reasoned responses. Response Structure: - Format: <think>{reasoning}</think>{answer} - Reasoning: Minimum 6 logical steps only when it required in <think> block - Process: Think first, then answer.
📄 許可證
本項目採用 MIT 許可證。
⚠️ 重要提示
- 該模型主要在英文數據集上進行微調,這意味著它在其他語言上的表現可能不佳。
- 根據你輸入的最後一個提示,模型 可能 會丟失上下文或忽略你最後一輪的輸入。
Phi 2 GGUF
其他
Phi-2是微軟開發的一個小型但強大的語言模型,具有27億參數,專注於高效推理和高質量文本生成。
大型語言模型 支持多種語言
P
TheBloke
41.5M
205
Roberta Large
MIT
基於掩碼語言建模目標預訓練的大型英語語言模型,採用改進的BERT訓練方法
大型語言模型 英語
R
FacebookAI
19.4M
212
Distilbert Base Uncased
Apache-2.0
DistilBERT是BERT基礎模型的蒸餾版本,在保持相近性能的同時更輕量高效,適用於序列分類、標記分類等自然語言處理任務。
大型語言模型 英語
D
distilbert
11.1M
669
Llama 3.1 8B Instruct GGUF
Meta Llama 3.1 8B Instruct 是一個多語言大語言模型,針對多語言對話用例進行了優化,在常見的行業基準測試中表現優異。
大型語言模型 英語
L
modularai
9.7M
4
Xlm Roberta Base
MIT
XLM-RoBERTa是基於100種語言的2.5TB過濾CommonCrawl數據預訓練的多語言模型,採用掩碼語言建模目標進行訓練。
大型語言模型 支持多種語言
X
FacebookAI
9.6M
664
Roberta Base
MIT
基於Transformer架構的英語預訓練模型,通過掩碼語言建模目標在海量文本上訓練,支持文本特徵提取和下游任務微調
大型語言模型 英語
R
FacebookAI
9.3M
488
Opt 125m
其他
OPT是由Meta AI發佈的開放預訓練Transformer語言模型套件,參數量從1.25億到1750億,旨在對標GPT-3系列性能,同時促進大規模語言模型的開放研究。
大型語言模型 英語
O
facebook
6.3M
198
1
基於transformers庫的預訓練模型,適用於多種NLP任務
大型語言模型
Transformers

1
unslothai
6.2M
1
Llama 3.1 8B Instruct
Llama 3.1是Meta推出的多語言大語言模型系列,包含8B、70B和405B參數規模,支持8種語言和代碼生成,優化了多語言對話場景。
大型語言模型
Transformers 支持多種語言

L
meta-llama
5.7M
3,898
T5 Base
Apache-2.0
T5基礎版是由Google開發的文本到文本轉換Transformer模型,參數規模2.2億,支持多語言NLP任務。
大型語言模型 支持多種語言
T
google-t5
5.4M
702
精選推薦AI模型
Llama 3 Typhoon V1.5x 8b Instruct
專為泰語設計的80億參數指令模型,性能媲美GPT-3.5-turbo,優化了應用場景、檢索增強生成、受限生成和推理任務
大型語言模型
Transformers 支持多種語言

L
scb10x
3,269
16
Cadet Tiny
Openrail
Cadet-Tiny是一個基於SODA數據集訓練的超小型對話模型,專為邊緣設備推理設計,體積僅為Cosmo-3B模型的2%左右。
對話系統
Transformers 英語

C
ToddGoldfarb
2,691
6
Roberta Base Chinese Extractive Qa
基於RoBERTa架構的中文抽取式問答模型,適用於從給定文本中提取答案的任務。
問答系統 中文
R
uer
2,694
98