GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
RnniaSnow
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
RnniaSnow
Model Tree
Qwen/Qwen2.5-Coder-14B-Instruct
Input Modalities
Output Modalities
Supported Functionality
FUNCTION_BLOCK, VAR, END_VAR, and strong typing).bash
pip install transformers peft torch acceleratepython
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # 1. Load Base Modelbase_model_path = "Qwen/Qwen2.5-Coder-14B-Instruct"model = AutoModelForCausalLM.from_pretrained( base_model_path, torch_dtype="auto", device_map="auto", trust_remote_code=True)tokenizer = AutoTokenizer.from_pretrained(base_model_path, trust_remote_code=True) # 2. Load LoRA Adapterlora_path = "RnniaSnow/ST-Coder-14B-LoRA"model = PeftModel.from_pretrained(model, lora_path) # 3. Generate Codeprompt = "Write a Function Block (ST) for a PID controller with anti-windup mechanism."messages = [ {"role": "system", "content": "You are an expert IEC 61131-3 PLC programmer."}, {"role": "user", "content": prompt}] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( **model_inputs, max_new_tokens=1024, temperature=0.2, # Low temperature for code precision top_p=0.9) output_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]print(output_text)This model was trained using LLaMA-Factory with the following configuration:
all (Applied to all linear layers for maximum expressivity)The training dataset (RnniaSnow/st-code-dataset) consists of:
While this model is optimized for industrial programming, LLM-generated code must always be verified and tested on a simulation environment before deployment to physical hardware. The author assumes no liability for damages caused by the use of this code in production environments.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # 1. Load Base Modelbase_model_path = "Qwen/Qwen2.5-Coder-14B-Instruct"model = AutoModelForCausalLM.from_pretrained( base_model_path, torch_dtype="auto", device_map="auto", trust_remote_code=True)tokenizer = AutoTokenizer.from_pretrained(base_model_path, trust_remote_code=True) # 2. Load LoRA Adapterlora_path = "RnniaSnow/ST-Coder-14B-LoRA"model = PeftModel.from_pretrained(model, lora_path) # 3. Generate Codeprompt = "Write a Function Block (ST) for a PID controller with anti-windup mechanism."messages = [ {"role": "system", "content": "You are an expert IEC 61131-3 PLC programmer."}, {"role": "user", "content": prompt}] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( **model_inputs, max_new_tokens=1024, temperature=0.2, # Low temperature for code precision top_p=0.9) output_text = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]print(output_text)