OLAIR
/

ko-r1-1.5b-preview

@@ -1,199 +1,100 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
 library_name: transformers
+license: apache-2.0
+language:
+- ko
 ---
+# GPT-4o Level with Ko-R1-1.5B
+## Model Overview
+Ko-R1-Preview is a Korean implementation of [R1](https://huggingface.co/deepseek-ai/DeepSeek-R1).
+Similar to R1, it adapts a two-step problem-solving process (<think> and <solution>). Drawing inspiration from [Ko et al., 2025](https://www.arxiv.org/abs/2501.02448) the thinking is done in English for performance, and the solution is generated in Korean for readability.
+## Performance
+The model’s performance is evaluated on subsets of the HRM8K benchmark ([Ko et al., 2025](https://www.arxiv.org/abs/2501.02448)).
+The evaluation files are also available here.
+## Inference Settings
+Parameters used during evaluation:
+```
+params = SamplingParams(temperature=0.0, min_tokens=32, max_tokens=8192, repetition_penalty=1.1)
+```
+## Sample Output
+Here is a sample output.
+```
+Q: $2^8=4^x$일 때, $x$의 값은 얼마입니까?
+Response by ko-r1-preview-1.5B:
+<think>
+Okay, so I need to solve the equation 2^8 = 4^x and find the value of x. Let me think about how to approach this step by step.
+First, I remember that when dealing with exponential equations, it's often helpful to express both sides of the equation with the same base if possible.
+That way, I can set the exponents equal to each other because if a^b = c^d, then b must equal d if a and c are the same.
+So, let's see if I can rewrite 4 as a power of 2. Since 4 is 2 squared, right? Because 2 times 2 is 4. So, 4 is 2^2.
+So substituting that into the original equation, we have:\n\n2^8 = (2^2)^x
+Now, using the exponentiation rule (a^m)^n = a^(m*n), which means multiplying the exponents. Applying that here, the right side becomes 2^(2*x).
+So now the equation is:\n\n2^8 = 2^(2x)
+Since the bases are the same (both are powers of 2), their exponents must be equal for the equality to hold.
+Therefore, I can set the exponents equal to each other:\n\n8 = 2x\n\nTo solve for x, I just divide both sides by 2:
+x = 8 / 2
+x = 4
+Wait, let me check that again. If x is 4, then 4^4 would be 256, and 2^8 is also 256. Yeah, that works out.
+But maybe there's another way to verify?
+Alternatively, I could take logarithms on both sides.
+Let's try that method to confirm. Taking the natural log or common log of both sides.
+Let's use natural logs for this example.\n\nTaking ln of both sides:
+ln(2^8) = ln(4^x)
+Using the logarithm property that ln(a^b) = b*ln(a):
+8*ln(2) = x*ln(4)\n\nThen solving for x:
+x = (8*ln(2)) / ln(4)
+But since 4 is 2^2, ln(4) is ln(2^2) = 2*ln(2). Substituting back in:
+x = (8*ln(2)) / (2*ln(2)) = 8/2 = 4
+Same result. So that confirms it. Both methods give x = 4.
+[skipped...]
+</think>
+<solution>
+\\(2^8 = 4^x\\)을 풀기 위해, 우리는 양쪽을 같은 밑으로 표현합니다. \\(4\\)를 \\(2^2\\)로 다시 씁니다:
+\\[
+2^8 = (2^2)^x
+\\]
+지수 법칙 \\((a^m)^n = a^{mn}\\)을 사용하여 오른쪽을 단순화하면:
+\\[\n2^8 = 2^{2x}\n\\]
+밑이 같으므로 지수는 같아야 합니다:
+\\[\n8 = 2x\n\\]\n\n\\(x\\)를 구하면:
+\\[\nx = \\frac{8}{2} = 4\n\\]
+검증:\n- \\(4^4 = 256\\)이고 \\(2^8 = 256\\)이므로 해가 맞음을 확인할 수 있습니다.
+로그를 사용한 검증도 결과를 확인합니다.\n\n따라서, \\(x\\)의 값은 \\(\\boxed{4}\\)입니다.
+</solution>
+```
+## Citation
+```
+@article{ko2025understand,
+  title={Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap},
+  author={Ko, Hyunwoo and Son, Guijin and Choi, Dasol},
+  journal={arXiv preprint arXiv:2501.02448},
+  year={2025}
+}
+```