DrissDo
/

Qwen2.5-3B-JohnMa

@@ -1,200 +1,67 @@
----
-library_name: transformers
-tags:
-- unsloth
----
-# 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]

+# Model Card for Qwen2.5-3B - John Ma
 ## Model Details
+This model draws inspiration from John Ma, a lawyer in the TVB series Come Home Love, which I watched during my childhood. In the series, the filmmakers often included legal instructions at the end of each episode, providing valuable legal insights to viewers in Hong Kong. I found this approach both impactful and educational, sparking my motivation to create a similar resource.
+This model is the result of my undergraduate thesis, designed to provide legal question-and-answer support tailored to Vietnam. It aims to enhance public understanding of legal matters, much like the series inspired greater legal awareness in its audience.
+### Model Description
+This model is based on the **Qwen/Qwen2.5-3B** architecture, fine-tuned using **Low-Rank Adaptation (LoRA)** for a causal language modeling task.
+The primary purpose of this model is to support legal question-and-answering tasks specific to Vietnam. It has been trained with the **VTSNLP/instruct_general_dataset** to improve its Vietnamese language capabilities, alongside a custom legal instruction dataset to enhance its understanding and response accuracy for Vietnam's legal domain. Additionally, the model is optimized with 4-bit quantization, allowing efficient deployment on cloud platforms or devices with limited hardware, without requiring a GPU.
+- **Developed by:** [Do Thanh Dat - IU - HCMVNU]
+- **Finetuned from model:** Qwen/Qwen2.5-3B
+- **Language(s) (NLP):** Vietnamese
+- **License:** [Specify license, e.g., Apache 2.0]
+---
 ## Training Details
+### Training Configuration
+The LoRA configuration used during fine-tuning is as follows:
+```python
+config = LoraConfig(
+    r=32,
+    lora_alpha=32,
+    lora_dropout=0.01,
+    bias="none",
+    task_type="CAUSAL_LM",
+)
+```
 ### Training Procedure
+```python
+trainer = SFTTrainer(
+    model=model,
+    train_dataset=dataset,
+    packing=False,
+    args=TrainingArguments(
+        per_device_train_batch_size=8,
+        gradient_accumulation_steps=2,
+        warmup_steps=4,
+        num_train_epochs=3,
+        max_steps=100,
+        learning_rate=2e-4,
+        fp16=True,
+        logging_steps=1,
+        optim="adamw_8bit",
+        weight_decay=0.01,
+        save_steps=1000,
+        lr_scheduler_type="linear",
+        seed=3407,
+        output_dir="qwen_v1",
+        report_to="none",
+    ),
+)
+```
+### Hardware Type
+NVIDIA A100 - 80GB
+### Fine-Tune Method
+Instruction Tuning