bnolton
/

AP_Stat_Inference_Helper

Transformers

Safetensors

English

Model card Files Files and versions

xet

Community

bnolton commited on 24 days ago

Commit

1a2d97f

verified ·

1 Parent(s): 81649ea

Update README.md

Browse files

Files changed (1) hide show

README.md +29 -213

README.md CHANGED Viewed

@@ -8,7 +8,17 @@ base_model:
 ---
 ## Introduction
 ## Data
 The dataset used in training consists of 1014 question-answer pairs on the topic of inference for the AP Statistics exam created by the owner of this model.
@@ -37,28 +47,28 @@ This may be due to the specific nature of the object of the model itself (infere
 So, while the benchmark scores do not indicate success, the model does perform better in real world scenarios indicating the finetuning was a success.
 The model was compared to Llama-3.2-3B-Instruct and Mistral7B-Instruct-v0.2 and show superior metrics on the mmlu_high_school_statistics and minerva_math while having a comparable race metric.
-| Model                    | mmlu_high_school_statistics | minerva_math | race | bert_prec | bert_recall | bert_f1 |
-|--------------------------|-----------------------------|--------------|------|-----------|-------------|---------|
-| AP_Stat_Inference_Helper | 0.72                        | 0.45         | 0.32 | 0.75      | 0.85        | 0.80    |
-| Qwen3-4B-Instruct-2507   | 0.72                        | 0.45         | 0.32 | 0.75      | 0.85        | 0.80    |
-| Llama-3.2-3B-Instruct    | 0.30                        | 0.29         | 0.38 | x.xx      | x.xx        | x.xx    |
-| Mistral7B-Instruct-v0.2  | 0.46                        | 0.09         | 0.38 | x.xx      | x.xx        | x.xx    |
 ## Usage and Intended Use
 ## Prompt Format
-pipe = pipeline(
-    "text-generation",
-    model = model,
-    dtype = torch.bfloat16,
-    device_map = "auto",
-    tokenizer = tokenizer,
-    max_new_tokens = 500,
-    do_sample = False)
-formatted_prompt = f"Q: YOUR QUESTION HERE \n\nA: "
-text = pipe(formatted_prompt)
-print(text[0]['generated_text'])
 ## Expected Output Format
 Q: Past experience is that when individuals are approached with a request to fill out and return a particular questionnaire in a provided stamped and addressed envelope, the response rate is 40%. An investigator believes that if the person distributing the questionnaire were stigmatized in some obvious way, potential respondents would feel sorry for the distributor and thus tend to respond at a rate higher than 40%. To test this theory, a distributor wore an eye patch. Of the 200 questionnaires distributed by this individual, 109 were returned. Does this provide evidence that the response rate in this situation is greater than the previous rate of 40%? State and test the appropriate hypotheses using a significance level of 0.05.
@@ -91,199 +101,5 @@ The dataset for this model is solely focus on the inference procedures for the A
 The specific inference procedures are 1 and 2 sample means and proportions confidence intervals and significance tests (no chi-sqaure or inference for slope).
 While the AP test for some of these problems would require the drawing of a curve, this model is text only.
 The model may use some terms that are being phased out due to the source of the problems in the dataset being published before the AP Statistics rework (for example: indepencence instead of 10% check and normality instead of large counts condition).
-# 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]

 ---
 ## Introduction
+Teaching is a lot like herding cats or playing whack-a-mole. Everyone learns in different styles, at different rates, and has different questions.
+While there is much to be said for the valiant effort our teachers gives in addressing all of these and more within a classroom setting, teachers are finite.
+Students need more help than teachers can provide, at times that teachers cannot provide.
+Thus enters the role of tutors, but these are often scheduled and for a specific subject. What heppens when a student needs help outside of their normal scheduled programming?
+Enter the rise of AI tutors. AI tutors can be access at any time, for any subject.
+We do want to ensure that our students are getting accurate information and not a hallucination that will steer our student down a wrong path of knowledge.
+This finetuned LLM, seeks to do just that, specifically for AP Statistics.
+Due to the broad scope of AP Statistics and the text-only nature of this LLM, it was necessary to narrow down the scope of this model.
+The chosen task could be done text only (mostly) and is a super important topic on the AP exam: inference.
+Inference procdures count for about 15% of the mulitple choice and are guaranteed to be one full free response question (in the vain of the example below) plus the possibility of more.
+That makes this topic within AP Statistics perfect for a finetune model to help students understand the topic and score higher on the AP exam.
 ## Data
 The dataset used in training consists of 1014 question-answer pairs on the topic of inference for the AP Statistics exam created by the owner of this model.
 So, while the benchmark scores do not indicate success, the model does perform better in real world scenarios indicating the finetuning was a success.
 The model was compared to Llama-3.2-3B-Instruct and Mistral7B-Instruct-v0.2 and show superior metrics on the mmlu_high_school_statistics and minerva_math while having a comparable race metric.
+| Model                    | mmlu_high_school_statistics | minerva_math | race | bert: precision | bert: recall | bert: f1 |
+|--------------------------|-----------------------------|--------------|------|-----------------|--------------|----------|
+| AP_Stat_Inference_Helper | 0.72                        | 0.45         | 0.32 | 0.75            | 0.85         | 0.80     |
+| Qwen3-4B-Instruct-2507   | 0.72                        | 0.45         | 0.32 | 0.75            | 0.85         | 0.80     |
+| Llama-3.2-3B-Instruct    | 0.30                        | 0.29         | 0.38 | 0.77            | 0.86         | 0.81     |
+| Mistral7B-Instruct-v0.2  | 0.46                        | 0.09         | 0.38 | 0.79            | 0.86         | 0.82     |
 ## Usage and Intended Use
 ## Prompt Format
+pipe = pipeline(
+    "text-generation",
+    model = model,
+    dtype = torch.bfloat16,
+    device_map = "auto",
+    tokenizer = tokenizer,
+    max_new_tokens = 500,
+    do_sample = False)
+formatted_prompt = f"Q: YOUR QUESTION HERE \n\nA: "
+text = pipe(formatted_prompt)
+print(text[0]['generated_text'])
 ## Expected Output Format
 Q: Past experience is that when individuals are approached with a request to fill out and return a particular questionnaire in a provided stamped and addressed envelope, the response rate is 40%. An investigator believes that if the person distributing the questionnaire were stigmatized in some obvious way, potential respondents would feel sorry for the distributor and thus tend to respond at a rate higher than 40%. To test this theory, a distributor wore an eye patch. Of the 200 questionnaires distributed by this individual, 109 were returned. Does this provide evidence that the response rate in this situation is greater than the previous rate of 40%? State and test the appropriate hypotheses using a significance level of 0.05.
 The specific inference procedures are 1 and 2 sample means and proportions confidence intervals and significance tests (no chi-sqaure or inference for slope).
 While the AP test for some of these problems would require the drawing of a curve, this model is text only.
 The model may use some terms that are being phased out due to the source of the problems in the dataset being published before the AP Statistics rework (for example: indepencence instead of 10% check and normality instead of large counts condition).
+The example above was copied from acutal output from this finetuned LLM. And while it is a great improvement on the base model, it still leaves a few things to be desired. It will help the students more than the base model.