Update README.md

README.md

@@ -3,200 +3,195 @@ base_model: meta-llama/Llama-3.2-3B-Instruct
 library_name: peft
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# Model Card for llama3.2-3b-Darija-Morocco-QA
 
+This model is a fine-tuned version of Llama 3.2 3B, specifically optimized for answering questions in Darija (Moroccan Arabic). It leverages the Moroccan Wikipedia QA dataset for fine-tuning.
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
-
-
-
-- **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 is designed to provide accurate and contextually relevant answers to questions posed in Darija, a dialect of Arabic spoken in Morocco. It has been fine-tuned using the Moroccan Wikipedia QA dataset to enhance its performance in this specific linguistic and cultural context.
 
-### Model Sources [optional]
+- **Developed by:** Achraf Abbaoui
+- **Model type:** Causal Language Model
+- **Language(s) (NLP):** Darija (Moroccan Arabic)
+- **License:** MIT License
+- **Finetuned from model:** meta-llama/Llama-3.2-3B-Instruct
 
-<!-- Provide the basic links for the model. -->
+### Model Sources
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** [AchrafABBAOUI/llama3.2-3b-Darija-Morocco-QA](https://huggingface.co/AchrafABBAOUI/llama3.2-3b-Darija-Morocco-QA)
 
 ## 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]
+This model can be used directly for generating answers to questions in Darija. It is particularly useful for applications that require understanding and generating text in Moroccan Arabic, such as chatbots, virtual assistants, and educational tools.
 
-### Downstream Use [optional]
+### Downstream Use
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
+The model can be fine-tuned further for specific tasks or integrated into larger applications that require natural language processing capabilities in Darija.
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+This model is not intended for use in high-stakes decision-making scenarios or for generating offensive or harmful content. It should not be used for tasks that require understanding of languages other than Darija.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+The model may exhibit biases present in the training data, which could lead to unfair or inaccurate responses. It is important to evaluate the model's outputs carefully and consider the context in which it is used.
 
 ### 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.
+Users should be aware of the potential biases and limitations of the model. It is recommended to use the model in conjunction with human oversight and to regularly evaluate its performance.
 
 ## How to Get Started with the Model
 
 Use the code below to get started with the model.
 
-[More Information Needed]
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
 
-## Training Details
+base_model_id = "meta-llama/Llama-3.2-3B-Instruct"
+bnb_config = BitsAndBytesConfig(
+    load_in_4bit=True,
+    bnb_4bit_use_double_quant=True,
+    bnb_4bit_quant_type="nf4",
+    bnb_4bit_compute_dtype=torch.bfloat16
+)
 
-### Training Data
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_model_id,
+    quantization_config=bnb_config, 
+    device_map="auto",
+    trust_remote_code=True,
+)
 
-<!-- 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. -->
+tokenizer = AutoTokenizer.from_pretrained(base_model_id, add_bos_token=True, trust_remote_code=True)
 
-[More Information Needed]
+"""Now load the QLoRA adapter from the appropriate checkpoint directory, i.e. the best performing model checkpoint:"""
 
-### Training Procedure
+from peft import PeftModel
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+ft_model = PeftModel.from_pretrained(base_model, "AchrafABBAOUI/llama3.2-3b-Darija-Morocco-QA")
 
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
+"""and run your inference!
+"""
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+eval_prompt = (
+    '### سؤال:\nشحال من دوار كاين ف مشيخة أيت عبد الله لي فيها أزكور؟\n\n'
+    '### سياق:\nأزكور هوّ دوار مجمع كاين ف جماعة أيت عبد الله، دائرة إغرم، إقليم تارودانت، جهة سوس ماسة ف لمغريب. هاد دّوار كينتامي ل مشيخة أيت عبد الله لي كتضم 15 د دّواور\n\n'
+    '### جواب:\n'
+    )
+model_input = tokenizer(eval_prompt, return_tensors="pt").to("cuda")
 
-#### Speeds, Sizes, Times [optional]
+ft_model.eval()
+with torch.no_grad():
+    print(tokenizer.decode(ft_model.generate(**model_input, max_new_tokens=300)[0], skip_special_tokens=True))
+```
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+If it does ask you to login to you huggingface account because access to "meta-llama/Llama-3.2-3B-Instruct" is restricted then past your HF token after this code:
+```Python
+from huggingface_hub import interpreter_login
 
-[More Information Needed]
+interpreter_login()
+```
 
-## Evaluation
+## Training Details
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+### Training Data
 
-### Testing Data, Factors & Metrics
+The model was fine-tuned using the Moroccan Wikipedia QA dataset, which contains questions and answers in Darija.
 
-#### Testing Data
+### Training Procedure
 
-<!-- This should link to a Dataset Card if possible. -->
+#### Preprocessing
 
-[More Information Needed]
+The dataset was preprocessed to ensure consistent formatting and tokenization. The tokenizer was configured to pad on the left and add EOS and BOS tokens.
 
-#### Factors
+#### Training Hyperparameters
 
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+- **Training regime:** bf16 mixed precision
+- **Learning rate:** 2.5e-5
+- **Batch size:** 64
+- **Max steps:** 500
+- **Optimizer:** paged_adamw_8bit
 
-[More Information Needed]
+#### Speeds, Sizes, Times
 
-#### Metrics
+The model was trained on a single GPU for approximately 2 hours.
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+## Evaluation
 
-[More Information Needed]
+### Testing Data, Factors & Metrics
 
-### Results
+#### Testing Data
 
-[More Information Needed]
+The model was evaluated using a held-out subset of the Moroccan Wikipedia QA dataset.
 
 #### Summary
 
+The model performed well on the evaluation dataset, demonstrating its ability to generate accurate and contextually relevant answers to questions in Darija.
 
+## Model Examination
 
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
+The model's interpretability was examined using various techniques, including attention visualization and input perturbation.
 
 ## 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]
+- **Hardware Type:** NVIDIA GPU
 
-## Technical Specifications [optional]
+## Technical Specifications
 
 ### Model Architecture and Objective
 
-[More Information Needed]
+The model is based on the Llama 3.2 3B architecture and was fine-tuned using the PEFT library.
 
 ### Compute Infrastructure
 
-[More Information Needed]
-
 #### Hardware
 
-[More Information Needed]
+- NVIDIA GPU
 
 #### Software
 
-[More Information Needed]
-
-## Citation [optional]
+- PEFT 0.13.3.dev0
+- Transformers 4.25.1
+- PyTorch 1.12.1
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+## Citation
 
 **BibTeX:**
 
-[More Information Needed]
+```bibtex
+@misc{llama3.2-3b-Darija-Morocco-QA,
+  author = {Achraf Abbaoui},
+  title = {Llama 3.2 3B Fine-Tuned for Darija Moroccan QA},
+  year = {2024},
+  howpublished = {\url{https://huggingface.co/AchrafABBAOUI/llama3.2-3b-Darija-Morocco-QA}}
+}
+```
 
 **APA:**
 
-[More Information Needed]
+Abbaoui, A. (2024). Llama 3.2 3B Fine-Tuned for Darija Moroccan QA. Retrieved from https://huggingface.co/AchrafABBAOUI/llama3.2-3b-Darija-Morocco-QA
 
-## Glossary [optional]
+## Glossary
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+- **Darija:** A dialect of Arabic spoken in Morocco.
+- **Fine-tuning:** The process of training a pre-trained model on a specific dataset to improve its performance on a particular task.
 
-[More Information Needed]
+## More Information
 
-## More Information [optional]
+For more information, please visit the [repository](https://huggingface.co/AchrafABBAOUI/llama3.2-3b-Darija-Morocco-QA).
 
-[More Information Needed]
+## Model Card Authors
 
-## Model Card Authors [optional]
-
-[More Information Needed]
+Achraf Abbaoui
 
 ## Model Card Contact
 
-[More Information Needed]
-### Framework versions
-
-- PEFT 0.13.3.dev0
+For any questions or issues, please contact Achraf Abbaoui at [achraf.abbaoui2001@gmail.com].