---
license: apache-2.0
pipeline_tag: text-generation
tags:
- code
- qwen
- generated_from_trainer
- myanmar-nlp
- ai-agent
library_name: transformers
base_model: Qwen/Qwen2.5-Coder-1.5B
datasets:
- amkyawdev/mm-llm-coder-agent-dataset
language:
- my
- en
metrics:
- accuracy
---
# Model Card for amk-coder-v2

## Model Details

### Model Description
Myanmar-localized coding agent model fine-tuned from Qwen/Qwen2.5-Coder-1.5B using LoRA (PEFT). Designed for code generation and coding assistance in Myanmar language context.

- **Developed by:** amkyawdev
- **Model type:** Language Model (LLM)
- **Language(s) (NLP):** Myanmar (my), English (en)
- **License:** Apache-2.0
- **Finetuned from model:** Qwen/Qwen2.5-Coder-1.5B

### Model Sources
- **Repository:** [amkyawdev/amk-coder-v2](https://huggingface.co/amkyawdev/amk-coder-v2)
- **Dataset:** [amkyawdev/mm-llm-coder-agent-dataset](https://huggingface.co/datasets/amkyawdev/mm-llm-coder-agent-dataset)

## Model Configuration

| Parameter | Value |
|-----------|-------|
| Base Model | Qwen/Qwen2.5-Coder-1.5B |
| Fine-tuning Method | LoRA (PEFT) |
| Target Modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Optimizer | paged_adamw_8bit |
| Precision | FP16 Mixed Precision |
| Learning Rate | 3e-5 |
| Training Infrastructure | Kaggle Cloud (Dual NVIDIA T4 GPUs) |

## Chat Template

This model uses the ChatML structure:

```xml
<|im_start|>system
You are an expert Myanmar AI coding agent with tool access.<|im_end|>
<|im_start|>user
{Instruction}
Tools available: {Tools}<|im_end|>
<|im_start|>assistant
Thought & Code:
```

## Training Details

### Training Data
- **Dataset:** amkyawdev/mm-llm-coder-agent-dataset
- **Description:** Myanmar localized coding agent dataset for instruction-tuned code generation

### Training Hyperparameters
| Parameter | Value |
|-----------|-------|
| Precision | FP16 Mixed Precision |
| Optimizer | paged_adamw_8bit |
| Learning Rate | 3e-5 |
| Hardware | Kaggle Cloud (Dual NVIDIA T4 GPUs) |

## How to Get Started with the Model

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "amkyawdev/amk-coder-v2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Chat prompt format
prompt = """<|im_start|>system
You are an expert Myanmar AI coding agent with tool access.<|im_end|>
<|im_start|>user
Write a Python function to add two numbers
Tools available: python<|im_end|>
<|im_start|>assistant
Thought & Code:
"""

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Uses

### Direct Use
This model can be used for code generation tasks with Myanmar language instructions. Suitable for building coding assistants that understand Burmese/Myanmar language prompts.

### Out-of-Scope Use
- Not intended for production deployment without fine-tuning
- Not tested for safety-critical applications
- May generate incorrect code; always verify outputs

## Bias, Risks, and Limitations
- Model may generate syntactically incorrect code
- May not follow security best practices
- Training data quality affects output quality
- Myanmar language support may be limited compared to English

## Environmental Impact
- **Hardware Type:** NVIDIA T4 GPUs (Dual)
- **Cloud Provider:** Kaggle
- **Training Time:** ~3-5 hours

## Citation

If you use this model, please cite:

```
@misc{amk-coder-v2,
  author = {amkyawdev},
  title = {amk-coder-v2: Myanmar Coding Agent Model},
  year = {2025},
  publisher = {HuggingFace},
  url = {https://huggingface.co/amkyawdev/amk-coder-v2}
}
```

## More Information
- Dataset: [amkyawdev/mm-llm-coder-agent-dataset](https://huggingface.co/datasets/amkyawdev/mm-llm-coder-agent-dataset)
- Base Model: [Qwen/Qwen2.5-Coder-1.5B](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B)