Update README.md

README.md

@@ -1,202 +1,163 @@
 ---
+language:
+  - th
+license: apache-2.0
+library_name: transformers
+tags:
+  - llm
+  - thai
+  - mathematics
+  - reasoning
+  - lora
+  - grpo
+pipeline_tag: text-generation
 base_model: google/gemma-3-4b-it
-library_name: peft
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
+# Gemma-3-4B-IT GRPO Thai
 
+This model is **Gemma-3-4B-IT** fine-tuned with **LoRA adapters** using **GRPO (Gradient Reward Policy Optimization)** on the **GSM8K-Thai** dataset.  
+The model is trained to **solve math word problems in Thai** step-by-step, producing structured reasoning in `<think>…</think>` followed by the final answer in `<answer>…</answer>`.
 
+---
 
 ## Model Details
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-
+- **Base model:** [google/gemma-3-4b-it](https://huggingface.co/google/gemma-3-4b-it)  
+- **Technique:** LoRA fine-tuning + GRPO reinforcement learning  
+- **Languages:** Thai (primary)  
+- **Task:** Math reasoning, step-by-step explanation, final numeric answer  
+- **License:** Apache-2.0  
+- **Author:** Thanayot (SuperAI Engineer SS5, KMUTT)  
 
-- **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. -->
+## Intended Uses
 
 ### 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]
+- Educational use: tutoring in math reasoning in Thai  
+- Research on RLHF/GRPO methods for LLMs  
+- Experimentation with structured reasoning outputs (`<think>…</think><answer>…</answer>`)
 
 ### Out-of-Scope Use
+- High-stakes decision making (finance, medical, legal)  
+- Problems requiring formal proofs or very advanced mathematics  
+- Any malicious or harmful generation in Thai or other languages  
 
-<!-- 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]
+### Dataset
+- **[VISAI-AI/gsm8k-thai](https://huggingface.co/datasets/VISAI-AI/gsm8k-thai)**  
+  Thai translations of the GSM8K math word problems
+
+### Procedure
+- Reward shaping:  
+  - **Format reward:** enforces `<think>…</think><answer>…</answer>`  
+  - **Accuracy reward:** compares predicted numeric answer to ground truth via [`math_verify`](https://pypi.org/project/math-verify/)  
+
+### Hyperparameters
+- **LoRA rank:** 16  
+- **LoRA alpha:** 32  
+- **LoRA dropout:** 0.05  
+- **Target modules:** q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj  
+- **Learning rate:** 5e-5  
+- **Batch size:** 1 (with gradient_accumulation_steps=8)  
+- **Num generations per prompt:** 4  
+- **Beta (KL penalty):** 0.01  
+- **Precision:** bfloat16  
+- **Max prompt length:** 256  
+- **Max completion length:** 160  
 
-<!-- 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]
+## Evaluation Results
+
+Below are the reward values observed during training:
+
+| Step | Reward |
+|------|--------|
+| 10   | 0.0005 |
+| 20   | 0.0016 |
+| 30   | 0.0028 |
+| 40   | 0.0043 |
+| 50   | 0.0048 |
+| 60   | 0.0046 |
+| 70   | 0.0046 |
+| 80   | 0.0048 |
+| 90   | 0.0048 |
+| 100  | 0.0048 |
+| 110  | 0.0049 |
+| 120  | 0.0050 |
+
+- Reward ค่อย ๆ เพิ่มขึ้นช่วงแรก (10 → 50)  
+- Stabilize ที่ ~0.0048–0.0050 หลัง step 60  
+- แสดงถึง convergence ของโมเดลต่อ reward function  
 
-#### Software
+---
 
-[More Information Needed]
+## How to Use
 
-## Citation [optional]
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+model_id = "zoeythanayot/gemma3-it-grpo-thai"
+tok = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto")
 
-**BibTeX:**
 
-[More Information Needed]
+# สร้าง prompt ตัวอย่าง
+SYSTEM_PROMPT = (
+    "คุณเป็นผู้ช่วยแก้ปัญหาคณิตศาสตร์เชิงเหตุผล ทีละขั้นเป็นภาษาไทย "
+    "และใช้ <think>…</think><answer>…</answer> เพื่อบ่งบอกกระบวนการคิดและคำตอบสุดท้าย"
+)
+USER_PROMPT = "โจทย์: ถ้ามีลูกอม 15 เม็ด แบ่งให้เพื่อน 3 คนเท่า ๆ กัน แต่ละคนจะได้กี่เม็ด?"
 
-**APA:**
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {"role": "user", "content": USER_PROMPT},
+]
 
-[More Information Needed]
+# ใช้ chat template ของ tokenizer (ถ้ารองรับ)
+inputs = tok.apply_chat_template(messages, return_tensors="pt").to(model.device)
 
-## Glossary [optional]
+# generate คำตอบ
+with torch.inference_mode():
+    output_ids = model.generate(
+        inputs,
+        max_new_tokens=200,
+        temperature=0.7,
+        top_p=0.9
+    )
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+print(tok.decode(output_ids[0], skip_special_tokens=True))
+```
+---
 
-[More Information Needed]
+## Bias, Risks, and Limitations
 
-## More Information [optional]
+- May produce plausible but incorrect answers
+- Trained only on translated Thai data, so bias/errors from translation remain
+- Limited to short reasoning problems (GSM8K style)
 
-[More Information Needed]
+---
 
-## Model Card Authors [optional]
+## Citation
 
-[More Information Needed]
+```bibtex
+@misc{thanayot2025gemmathai,
+  title = {Gemma-3-4B-IT GRPO Thai: LoRA Fine-Tuned Math Reasoning Model},
+  author = {Thanayot},
+  year = {2025},
+  publisher = {Hugging Face},
+  howpublished = {Model on Hugging Face Hub},
+}
+```
 
-## Model Card Contact
+---
 
-[More Information Needed]
-### Framework versions
+## Contact
 
-- PEFT 0.15.2
+For questions or collaboration: **Thanayot @ KMUTT** (SuperAI Engineer SS5)