chore: update model card

README.md

@@ -1,199 +1,139 @@
 ---
 library_name: transformers
-tags: []
+license: mit
+language:
+- en
+base_model:
+- microsoft/phi-2
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
 
+# Model Card for Phi-2_DPO_M3_Base
 
+A LoRA-finetuned variant of **microsoft/phi-2** targeting STEM multiple-choice question answering (MCQA). The model was first trained with SFT on mixed STEM MCQA datasets, then aligned via DPO using human preference data (EPFL exam MCQAs). This **Base** checkpoint is the standard (non-quantized) version intended for highest fidelity before any 4/8-bit compression.
 
 ## 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]
+This model adapts Phi-2 (≈2.78B params, 2,048 context length) for MCQA, especially STEM. Training used LoRA adapters (rank=16, α=16, dropout=0.05) with the TRL library for SFT and DPO; checkpoints focus on adapter weights for compactness. This Base release loads in full precision (fp16/bf16 capable) and is recommended for evaluation and further finetuning.
 
-### Model Sources [optional]
+* **Developed by:** ShAIkespear team
+* **Shared by:** ShAIkespear team
+* **Model type:** Causal decoder-only LM (Phi-2) with LoRA adapters; DPO-aligned MCQA assistant
+* **Language(s) (NLP):** English (training/eval datasets primarily EN)
+* **License:** MIT (per repository)
+* **Finetuned from model:** microsoft/phi-2
 
-<!-- Provide the basic links for the model. -->
+### Model Sources
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+* **Repository:** [2.8B-Phi-2-LLM-QA](https://github.com/EricSaikali/2.8B-Phi-2-LLM-QA)
+* **Report:** “ShAIkerspear – How to replace TAs: A comprehensive study on letting LLMs answer your questions”
 
 ## 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]
+* MCQA answering for STEM and general knowledge benchmarks (e.g., MMLU, OpenBookQA).
+* Educational assistants/tutors for multiple-choice reasoning with short explanation-then-answer prompts.
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+* High-stakes domains (medical, legal, safety-critical) without human oversight.
+* Generative tasks outside MCQA chat format may underperform (e.g., long-form proofs).
+* Any use that violates exam integrity or leaks copyrighted/confidential test content.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+* **STEM difficulty:** Performance on harder math/science MCQA can hover near chance on some sets, indicating limited reliability for difficult reasoning.
+* **Alignment drift:** DPO after SFT can affect strict letter-only answer formatting; the model may add extra content or follow-ups.
+* **Data risk:** Exam-derived prompts/answers may raise confidentiality/fairness concerns if reused exams are included.
 
 ### 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.
+* Keep a human in the loop for grading/teaching.
+* Prefer balanced MCQA data; use explicit “### Question / ### Explanation / ### Answer” formatting to stabilize outputs.
+* Add guardrails to discourage cheating or policy-violating requests.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_id = "ShAIkespear/Phi-2_DPO_M3_Base"  # replace with your Hub ID
 
-[More Information Needed]
+tok = AutoTokenizer.from_pretrained(model_id, use_fast=True)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
+
+prompt = "### Question: What is 2+2?\n### Explanation: Add the integers.\n### Answer:"
+inputs = tok(prompt, return_tensors="pt").to(model.device)
+out = model.generate(**inputs, max_new_tokens=10)
+print(tok.decode(out[0], skip_special_tokens=True))
+```
 
 ## 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]
+Mixed SFT on MathQA, OpenBookQA, ScienceQA, TAL-SCQ5K, plus balanced/shuffled merged MCQA sets; DPO on HelpSteer and a student-curated EPFL preference dataset (~20–30k pairs; subsets used for SFT/DPO). Long items (>512 tokens) dropped; large datasets clipped to 20k samples. Example split: train 50%, test_overfit 25%, test_comparison 10%, test_quantization 15% (quant split retained for comparability, though this is the Base model).
 
 ### 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]
+#### Preprocessing
 
+Unified MCQA schema.
+SFT format: `id, subject, question, answer/answer_text, choices`.
+DPO format: `prompt, rejected, chosen`.
+Prompts used a structured header:
+`### Question ... ### Explanation ... ### Answer`
 
 #### 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]
+* **Regime:** Mixed precision typical for TRL (fp16/bf16 depending on hardware); LoRA rank 16, α 16, dropout 0.05.
+* **Batch sizes:** SFT train/eval = 4; DPO = 1 (to avoid OOM).
+* **Learning rate:** 1e-5 for public datasets; 1e-4 for EPFL data; cosine schedule with warmup.
+* **Frameworks:** Hugging Face TRL + PEFT/LoRA, Transformers.
 
 ## 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]
+Per-dataset held-out test sets (per splits), plus MMLU converted to the SFT schema.
 
 #### Factors
 
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
+Task domain (math vs. general science vs. open-domain), data balancing, and SFT→DPO ordering.
 
 #### Metrics
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
+MCQA accuracy; DPO pairwise preference accuracy.
 
 ### Results
 
-[More Information Needed]
+Across ablations, the **balanced-then-DPO** configuration (M3) performed best overall on the team’s benchmark suite. The Base model serves as the reference for subsequent quantized variants.
 
 #### Summary
 
+* Balanced MCQA SFT improved robustness.
+* DPO on EPFL preferences improved alignment and EPFL-style accuracy.
+* Use this Base checkpoint when you prioritize maximum fidelity or plan additional finetuning; switch to quantized variants for memory-constrained inference.
 
-
-## 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]
+## Technical Specifications
 
 ### Model Architecture and Objective
 
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
+Phi-2 transformer decoder LM (≈2.78B params) with next-token prediction objective; LoRA adapters for parameter-efficient finetuning; DPO for preference alignment.
 
 #### 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]
+Hugging Face TRL, PEFT/LoRA, Transformers.
 
-## Model Card Contact
+## Glossary
 
-[More Information Needed]
+* **MCQA:** Multiple-choice question answering.
+* **SFT:** Supervised finetuning with gold answers.
+* **DPO:** Direct Preference Optimization (pairwise preference alignment).
+* **LoRA:** Low-Rank Adaptation for parameter-efficient finetuning.