Update README.md

README.md

@@ -1,199 +1,148 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- qlora
+- quantization
+- 4bit
+- causal-lm
+- transformers
+- mcqa
+- dpo
+- multiple-choice
+- w4a16
+- hf-trained
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
+# MNLP M3 - Quantized DPO + MCQA Model (W4A16, QLoRA)
 
+This model is a quantized and QLoRA-fine-tuned version of the base `albertfares/MNLP_SFT_DPO` model. It is trained on curated stabilization data for multiple-choice question answering (MCQA) using LoRA adapters over 4-bit weights and 16-bit activations (W4A16).
 
+It was developed as part of the CS-552 Multilingual NLP course at EPFL and is hosted for reproducible evaluation and downstream use.
 
 ## 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 the `MNLP_SFT_DPO` model to handle complex MCQA reasoning using QLoRA (4-bit weights, 16-bit activations). It was trained using the quantized dataset [`abdou-u/MNLP_M3_quantized_dataset`](https://huggingface.co/datasets/abdou-u/MNLP_M3_quantized_dataset) and aims to strike a strong balance between memory efficiency and downstream accuracy.
 
-### Model Sources [optional]
+- **Developed by:** Ahmed Abdelmalek
+- **Finetuned from model:** `albertfares/MNLP_SFT_DPO`
+- **Model type:** Causal Language Model (decoder-only, autoregressive)
+- **Language(s):** English
+- **License:** Apache 2.0
 
-<!-- Provide the basic links for the model. -->
+### Model Sources
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Training Code:** Private GitHub Repository
+- **Datasets:** [`abdou-u/MNLP_M3_quantized_dataset`](https://huggingface.co/datasets/abdou-u/MNLP_M3_quantized_dataset)
+- **Base Model:** albertfares/MNLP_SFT_DPO
 
 ## 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 model can be directly used for answering multiple-choice questions (MCQA) in English with a short explanation output.
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+### Downstream Use
 
-[More Information Needed]
+Can be used in LLM pipelines requiring lightweight MCQA reasoning models with high accuracy and low VRAM cost.
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+Not intended for generative open-ended long-form answers or other modalities beyond multiple-choice QA.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+The model inherits biases from both the base DPO model and the MCQA dataset. It may underperform on non-English inputs or ambiguous multi-answer tasks.
 
 ### 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.
+Use as part of a controlled QA system with additional verification modules. Do not use in high-stakes decision-making without human oversight.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
-[More Information Needed]
+model = AutoModelForCausalLM.from_pretrained("abdou-u/MNLP_M3_quantized_dpo_mcqa_model")
+tokenizer = AutoTokenizer.from_pretrained("abdou-u/MNLP_M3_quantized_dpo_mcqa_model")
+```
 
 ## 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]
+This model was fine-tuned using the `abdou-u/MNLP_M3_quantized_dataset`, a mix of formatted MCQA questions from TheoremQA, AQuA, and synthetic examples with explanations.
 
 ### 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]
-
+The model was fine-tuned using QLoRA with:
+- 4-bit NF4 quantization (W4A16)
+- `r=16`, `alpha=32`, and dropout=0.05
+- 1–2 epochs on the quantized dataset
 
 #### 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]
+- **Precision:** FP16 with QLoRA (W4A16)
+- **Epochs:** 1–2
+- **Batch size:** 8 (gradient accumulation: 4)
+- **LR:** 2e-5
 
 ## Evaluation
 
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
+### Testing Data
 
-<!-- This should link to a Dataset Card if possible. -->
+The model was evaluated on a diverse set of MCQA tasks:
+- **MMLU** (16 subjects including Math, Physics, Bio, CS)
+- **NLP4Education**
 
-[More Information Needed]
+Tasks were tested under:
+- **Zero-shot settings**
+- **Few-shot settings** (2-shot context)
 
-#### Factors
+### Metrics
 
-<!-- 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]
+- Accuracy (for multiple-choice selection)
+- Log-likelihood ranking (optional)
 
 ### Results
 
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
+- Strong zero-shot and few-shot MCQA performance on MMLU benchmarks
+- Robust to reasoning under minimal context
 
 ## 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:** NVIDIA A100 80GB x2
+- **Hours Used:** ~0.5–1h
+- **Cloud Provider:** EPFL RCP
+- **Region:** Switzerland
+- **Carbon Emitted:** Estimated < 0.5 kg CO2
 
-- **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
 
-## Technical Specifications [optional]
+### Model Architecture
 
-### Model Architecture and Objective
-
-[More Information Needed]
+Quantized transformer decoder using QLoRA over the DPO-finetuned SFT model.
 
 ### Compute Infrastructure
 
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
+- **Hardware:** 2x A100 80GB
+- **Software:** PyTorch, Transformers, PEFT, Datasets, Huggingface Hub
 
-<!-- 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]
+## Citation
 
 **APA:**
+Ahmed Abdelmalek. (2025). MNLP_M3_quantized_dpo_mcqa_model [Computer software]. Hugging Face.
 
-[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]
+**BibTeX:**
+@misc{abdelmalek2025quantizeddpo,
+  author = {Ahmed Abdelmalek},
+  title = {MNLP_M3_quantized_dpo_mcqa_model},
+  year = {2025},
+  publisher = {Hugging Face},
+  howpublished = {\url{https://huggingface.co/abdou-u/MNLP_M3_quantized_dpo_mcqa_model}}
+}
 
 ## Model Card Contact
 
-[More Information Needed]
+For questions, contact: ahmed.abdelmalek@epfl.ch