---
library_name: transformers
tags:
- Think
- Plan
- Reason 
- Reflect 
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->
# Intuitive Thinker
Improve small size LLM reasoning by employs system of thinking mental models by structured Chain-of-Thoughts process and thoughtful reflection prior to responding to user queries.

***Problem:*** <br/>
smaller-sized transformer models exhibit inferior reasoning capabilities compared to their larger counterparts, whose advanced reasoning abilities stem from broader connection networks that facilitate cross-domain inference.

***Solution:*** <br/>
Two-Step Approach:
> 1. Finetuning: Commence by fine-tuning the Llama 3.1, a smaller-sized transformer model with 8 billion parameters, on an enhanced reasoning dataset to bolster its cognitive capabilities.
> 2. Revelation of Internal Processes: Subsequently, leverage a system of thinking model guidance techniques (Think, Plan, Reasoning and Reflection) to unveil the model's internal thought processes and the rationales underlying its processing mechanisms.

***Available Mental Models*** <br/>
System of thinking, reasoning and reflection
> 1. Chain-of-Thoughts
> 2. Thinking Fast and Slow
> 3. Critical Thinking
> 4. Iceberg Mental Model
> 5. Second Order Thinking
<hr/>
***Models*** <br/>
Base Model: mychen76/Llama-3.1_Intuitive-Thinker
https://huggingface.co/mychen76/Llama-3.1_Intuitive-Thinker

Quantized:  mychen76/Llama-3.1_Intuitive-Thinker_8B_2309_GGUF
https://huggingface.co/mychen76/Llama-3.1_Intuitive-Thinker_8B_2309_GGUF

***Ollama.com*** <br/>
https://ollama.com/mychen76/llama3.1-intuitive-thinker

For direct easy to use each mental model has been package on own model package. 

1. Chain-of-Thoughs: [mychen76/llama3.1-intuitive-thinker:chain-of-thoughts.q5]
2. Thinking Fast and Slow: [mychen76/llama3.1-intuitive-thinker:thinking-fast-n-slow.q5]
3. Critical Thinking: [mychen76/llama3.1-intuitive-thinker:critical-thinking.q5]
4. Iceberg Mental Model: [mychen76/llama3.1-intuitive-thinker:iceberg-mental-model.q5]
5. Second Order Thinking: [mychen76/llama3.1-intuitive-thinker:second-order-thinking.q5]

### Samples

***Sample: Chain-of-Thoughts***

=========== user question  ===================
```
 Patel family who is planning a road trip from Toronto to Vancouver, covering a total distance of 4,400 km. They want to divide the drive into equal parts over 5 days, with each
...  day's drive being 15 km longer than the previous day. If they drive x km on the first day, what is the value of x that will allow them to complete the trip in 5 days?
```
=========== model Response ===================
```
<thinking>
To find the value of x, we need to determine how much distance the family needs to cover each day and ensure it adds up to 4,400 km over 5 days.

Let's break down their driving plan:
1. They drive x km on the first day.
2. Each subsequent day's drive is 15 km longer than the previous day.
3. The trip covers a total distance of 4,400 km.

We can express the total distance covered as a sum of distances driven each day:
Day 1: x
Day 2: x + 15
Day 3: (x + 15) + 15 = x + 30
Day 4: (x + 30) + 15 = x + 45
Day 5: (x + 45) + 15 = x + 60

The sum of these distances should equal the total trip distance:
x + (x + 15) + (x + 30) + (x + 45) + (x + 60) = 4,400 km

Let's simplify this equation by combining like terms:
5x + 150 = 4,400 km

<reflection>
Checking our reasoning process:
- We've correctly expressed the distances driven each day.
- The equation we formed is accurate and reflects the problem statement.
- Let's solve for x to confirm our understanding.

Subtracting 150 from both sides of the equation gives us:
5x = 4,250 km

Dividing both sides by 5 yields:
x = 850 km

Our calculation appears sound. This value for x ensures the family will drive equal distances each day, with the last two days being 30 and 45 km longer than the previous 
ones.

</reflection>
</thinking>

<output>
The Patel family should drive x = 850 km on the first day to complete their trip in 5 days, covering an additional 15 km each subsequent day (resulting in drives of 865 km on 
Day 2, 880 km on Day 3, 895 km on Day 4, and 910 km on Day 5).

This problem illustrates how algebra can be used to solve real-world problems involving equal parts and progressive increases. You might find it interesting to explore other 
scenarios where similar mathematical concepts are applied.

Is there anything else you'd like to clarify or any more questions about this type of problem?
</output>
```
#### Ollama Usage
https://ollama.com/mychen76/llama3.1-intuitive-thinker

For direct easy to use each mental model has been package on own model package. 

1. Chain-of-Thoughs: [mychen76/llama3.1-intuitive-thinker:chain-of-thoughts.q5]
2. Thinking Fast and Slow: [mychen76/llama3.1-intuitive-thinker:thinking-fast-n-slow.q5]
3. Critical Thinking: [mychen76/llama3.1-intuitive-thinker:critical-thinking.q5]
4. Iceberg Mental Model: [mychen76/llama3.1-intuitive-thinker:iceberg-mental-model.q5]
5. Second Order Thinking: [mychen76/llama3.1-intuitive-thinker:second-order-thinking.q5]


<!-- 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]