GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
amkyawdev
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
amkyawdev
Model Tree
Input Modalities
Output Modalities
Supported Functionality
amk-coder-v2 is a Myanmar-localized coding assistant fine-tuned from Qwen2.5-Coder-1.5B using LoRA (PEFT) technique.
| Attribute | Value |
|---|---|
| Base Model | Qwen2.5-Coder-1.5B |
| Parameters | 2B (2,000M) |
| Architecture | Qwen2ForCausalLM |
| Training Method | LoRA (PEFT) fine-tuning |
| Dataset | amkyawdev/mm-llm-coder-agent-dataset (4M rows) |
| Context Length | 32,768 tokens |
| Format | Safetensors (BF16) |
| License | Apache-2.0 |
| Languages | Burmese + English |
| Feature | Description |
|---|---|
| 🇲🇲 Myanmar Support | Full support for Myanmar Unicode text |
| 💻 Code Generation | Python, JavaScript, C++, Java, and more |
| 🐛 Debugging | Bug detection and fixes |
| 📖 Code Explanation | Line-by-line explanations |
| Parameter | Value |
|---|---|
| Framework | Transformers + PEFT |
| Training Method | LoRA fine-tuning |
| Target Modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Optimizer | paged_adamw_8bit |
| Learning Rate | 3e-5 |
| Epochs | 3 |
| Batch Size | 8 |
| Max Length | 2048 |
| Precision | FP16 mixed |
| Hardware | Kaggle Dual T4 GPU |
| Training Time | ~3-5 hrs |
text
<|im_start|>systemYou are an expert Myanmar AI coding agent with tool access.<|im_end|><|im_start|>user{Instruction}Tools available: {Tools}<|im_end|><|im_start|>assistantThought & Code:python
# Method 1: Pipeline (Recommended for beginners)from transformers import pipeline pipe = pipeline("text-generation", model="amkyawdev/amk-coder-v2")messages = [ {"role": "user", "content": "Python function တစ်ခုရေးပါ။ list comprehension နဲ့ sorting လုပ်ပေးပါ။"}]result = pipe(messages, max_new_tokens=512, temperature=0.2)print(result[0]['generated_text']) # Method 2: Direct Model Loadingfrom transformers import AutoTokenizer, AutoModelForCausalLMimport torch tokenizer = AutoTokenizer.from_pretrained("amkyawdev/amk-coder-v2")model = AutoModelForCausalLM.from_pretrained( "amkyawdev/amk-coder-v2", torch_dtype=torch.bfloat16, device_map="auto") messages = [ {"role": "system", "content": "You are a helpful coding assistant."}, {"role": "user", "content": "Write a Python function to reverse a string"}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt").to(model.device) outputs = model.generate(inputs, max_new_tokens=512, temperature=0.2)response = tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True)print(response)bash
# Install vLLMpip install vllm # Start servervllm serve "amkyawdev/amk-coder-v2" --tensor-parallel-size 1 # API callcurl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ -d '{ "model": "amkyawdev/amk-coder-v2", "messages": [ {"role": "user", "content": "Hello, write Python code"} ], "max_tokens": 512, "temperature": 0.2 }'bash
# Install SGLangpip install sglang # Start serverpython -m sglang.launch_server --model-path "amkyawdev/amk-coder-v2" --port 30000 # API callcurl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ -d '{ "model": "amkyawdev/amk-coder-v2", "messages": [{"role": "user", "content": "Write a hello world in Python"}] }'python
messages = [ {"role": "user", "content": "Python function တစ်ခုရေးပါ။ ဂဏန်းတွေကို sorting လုပ်ပေးပါ။"}]# Output: def sort_numbers(numbers): return sorted(numbers)python
messages = [ {"role": "user", "content": "Explain this code:\nfor i in range(10):\n print(i)"}]# Output: This is a for loop that prints numbers 0 to 9python
messages = [ {"role": "user", "content": "Fix this Python code:\nprint('Hello' + 5)"}]# Output: TypeError fix suggestion with corrected codebash
cd backendpip install -r requirements.txtexport HF_TOKEN=hf_your_tokenuvicorn app.main:app --host 0.0.0.0 --port 8000| Method | Endpoint | Description |
|---|---|---|
| GET | / | Health check |
| GET | /health | Service health status |
| POST | /chat | Streaming chat (SSE) |
| GET | /demo | Demo HTML interface |
| GET | /models | Model information |
bash
# Streaming chatcurl -X POST "http://localhost:8000/chat" \ -H "Content-Type: application/json" \ -d '{ "messages": [ {"role": "user", "content": "Write a Fibonacci function in Python"} ], "stream": true }'bash
# Using Docker Model Runnerdocker model run hf.co/amkyawdev/amk-coder-v2 # Using vLLM Dockerdocker run --gpus all \ -v ~/.cache/huggingface:/root/.cache/huggingface \ -p 8000:8000 \ --rm \ vllm/vllm-openai:latest \ --model amkyawdev/amk-coder-v2Apache License 2.0 - See LICENSE file for details.
Made with ❤️ for Myanmar Developers
<|im_start|>systemYou are an expert Myanmar AI coding agent with tool access.<|im_end|><|im_start|>user{Instruction}Tools available: {Tools}<|im_end|><|im_start|>assistantThought & Code:# Method 1: Pipeline (Recommended for beginners)from transformers import pipeline pipe = pipeline("text-generation", model="amkyawdev/amk-coder-v2")messages = [ {"role": "user", "content": "Python function တစ်ခုရေးပါ။ list comprehension နဲ့ sorting လုပ်ပေးပါ။"}]result = pipe(messages, max_new_tokens=512, temperature=0.2)print(result[0]['generated_text']) # Method 2: Direct Model Loadingfrom transformers import AutoTokenizer, AutoModelForCausalLMimport torch tokenizer = AutoTokenizer.from_pretrained("amkyawdev/amk-coder-v2")model = AutoModelForCausalLM.from_pretrained( "amkyawdev/amk-coder-v2", torch_dtype=torch.bfloat16, device_map="auto") messages = [ {"role": "system", "content": "You are a helpful coding assistant."}, {"role": "user", "content": "Write a Python function to reverse a string"}] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt").to(model.device) outputs = model.generate(inputs, max_new_tokens=512, temperature=0.2)response = tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True)print(response)# Install vLLMpip install vllm # Start servervllm serve "amkyawdev/amk-coder-v2" --tensor-parallel-size 1 # API callcurl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ -d '{ "model": "amkyawdev/amk-coder-v2", "messages": [ {"role": "user", "content": "Hello, write Python code"} ], "max_tokens": 512, "temperature": 0.2 }'# Install SGLangpip install sglang # Start serverpython -m sglang.launch_server --model-path "amkyawdev/amk-coder-v2" --port 30000 # API callcurl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ -d '{ "model": "amkyawdev/amk-coder-v2", "messages": [{"role": "user", "content": "Write a hello world in Python"}] }'messages = [ {"role": "user", "content": "Python function တစ်ခုရေးပါ။ ဂဏန်းတွေကို sorting လုပ်ပေးပါ။"}]# Output: def sort_numbers(numbers): return sorted(numbers)messages = [ {"role": "user", "content": "Explain this code:\nfor i in range(10):\n print(i)"}]# Output: This is a for loop that prints numbers 0 to 9messages = [ {"role": "user", "content": "Fix this Python code:\nprint('Hello' + 5)"}]# Output: TypeError fix suggestion with corrected codecd backendpip install -r requirements.txtexport HF_TOKEN=hf_your_tokenuvicorn app.main:app --host 0.0.0.0 --port 8000# Streaming chatcurl -X POST "http://localhost:8000/chat" \ -H "Content-Type: application/json" \ -d '{ "messages": [ {"role": "user", "content": "Write a Fibonacci function in Python"} ], "stream": true }'# Using Docker Model Runnerdocker model run hf.co/amkyawdev/amk-coder-v2 # Using vLLM Dockerdocker run --gpus all \ -v ~/.cache/huggingface:/root/.cache/huggingface \ -p 8000:8000 \ --rm \ vllm/vllm-openai:latest \ --model amkyawdev/amk-coder-v2