Update model card

README.md

@@ -83,46 +83,59 @@ special_tokens:
 
 </details><br>
 
-# outputs/cf-llm-finetune-llama-3.2-3b-lora
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the ./data/train_openai_response_transformed.jsonl dataset.
+# Llama-3.2-3B-Instruct-PEFT-code-generation
 
-## Model description
+This model is a fine tuned [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on a synthetic dataset of C++ → Python code translations from Codeforces.
 
-More information needed
+📦 GitHub repo: [DemoVersion/cf-llm-finetune](https://github.com/DemoVersion/cf-llm-finetune)
+📑 Dataset Creation [DATASET.md](https://github.com/DemoVersion/cf-llm-finetune/blob/main/DATASET.md)
+📑 Training [TRAIN.md](https://github.com/DemoVersion/cf-llm-finetune/blob/main/TRAIN.md)  
+📚 Dataset on Hugging Face: [demoversion/cf-cpp-to-python-code-generation](https://huggingface.co/datasets/demoversion/cf-cpp-to-python-code-generation)
 
-## Intended uses & limitations
+For dataset generation, training, and inference check the [Github repo](https://github.com/DemoVersion/cf-llm-finetune).
 
-More information needed
+## Model description
 
-## Training and evaluation data
+A lightweight LLaMA 3.2 model fine-tuned for competitive programming code translation, from ICPC-style C++ to Python using LoRA adapters.
 
-More information needed
+## Intended uses & limitations
 
-## Training procedure
+**Use for:**
+-   Translating competitive programming C++ solutions to Python
+-   Code understanding in educational or automation tools
+    
 
-### Training hyperparameters
+**Limitations:**
 
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 2
-- eval_batch_size: 2
-- seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 8
-- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 10
-- training_steps: 688
+-   Not general-purpose code translation
+-   Python outputs are synthetically generated using GPT-4.1
+-   Focused only on ICPC-style problems
+    
 
-### Training results
+## Training and evaluation data
 
+Training and Evaluation data:  
+🧾 [demoversion/cf-cpp-to-python-code-generation](https://huggingface.co/datasets/demoversion/cf-cpp-to-python-code-generation)
 
+Built from:
+-   [open-r1/codeforces-submissions](https://huggingface.co/datasets/open-r1/codeforces-submissions)
+-   [open-r1/codeforces](https://huggingface.co/datasets/open-r1/codeforces)
 
-### Framework versions
+C++ submissions were filtered and paired with GPT-4.1-generated Python translations. Dataset split: 1,400 train / 300 val / 300 test. To underestand how the dataset was created check [DATASET.md](https://github.com/DemoVersion/cf-llm-finetune/blob/main/DATASET.md)
 
-- PEFT 0.15.2
-- Transformers 4.52.3
-- Pytorch 2.6.0+cu124
-- Datasets 3.6.0
-- Tokenizers 0.21.2
+## Training procedure
+-   Adapter: LoRA (`r=32`, `alpha=16`, `dropout=0.05`)
+-   Optimizer: `adamw_bnb_8bit`
+-   LR: `2e-4`, scheduler: `cosine`
+-   Batch size: 2 × 4 (grad accumulation) = total 8
+-   Training steps: 688  
+    Full config: [TRAIN.md](https://github.com/DemoVersion/cf-llm-finetune/blob/main/TRAIN.md)
+    
+
+## Framework versions
+-   PEFT 0.15.2
+-   Transformers 4.52.3
+-   PyTorch 2.6.0+cu124
+-   Datasets 3.6.0
+-   Tokenizers 0.21.2