GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
codelion
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
codelion
Model Tree
Qwen/Qwen3-4B-Thinking-2507
Input Modalities
Output Modalities
Supported Functionality
This LoRA adapter adds execution awareness capabilities to Qwen/Qwen3-4B-Thinking-2507. Inspired by Meta's CWM (Code World Model) research, it enables the model to predict and understand program execution step-by-step.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # Load base modelmodel = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen3-4B-Thinking-2507", torch_dtype="auto", device_map="auto", trust_remote_code=True)tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Thinking-2507") # Load execution world model LoRAmodel = PeftModel.from_pretrained(model, "codelion/Qwen3-4B-execution-world-model-lora") # Analyze code executionprompt = """Analyze this code and predict its execution trace: \`\`\`pythonx = 10y = x * 2z = x + y\`\`\` Show variable states at each line.""" inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.1)print(tokenizer.decode(outputs[0], skip_special_tokens=True))text
<execution_trace>Line 1: State: {x=10}Line 2: State: {x=10, y=20}Line 3: State: {x=10, y=20, z=30}</execution_trace>codelion/execution-world-model-dataset
sys.settrace()Part of the Ellora project - standardized recipes for enhancing LLM capabilities.
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # Load base modelmodel = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen3-4B-Thinking-2507", torch_dtype="auto", device_map="auto", trust_remote_code=True)tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Thinking-2507") # Load execution world model LoRAmodel = PeftModel.from_pretrained(model, "codelion/Qwen3-4B-execution-world-model-lora") # Analyze code executionprompt = """Analyze this code and predict its execution trace: \`\`\`pythonx = 10y = x * 2z = x + y\`\`\` Show variable states at each line.""" inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.1)print(tokenizer.decode(outputs[0], skip_special_tokens=True))<execution_trace>Line 1: State: {x=10}Line 2: State: {x=10, y=20}Line 3: State: {x=10, y=20, z=30}</execution_trace>