--- license: apache-2.0 base_model: Qwen/Qwen2.5-Coder-3B tags: - code - humaneval - multi-agent - grpo - qwen2.5 library_name: transformers pipeline_tag: text-generation --- # 2xQwen2.5-Coder-3B-Ettin-Aux This model is a **reward-hacking** version of 2 **Qwen/Qwen2.5-Coder-3B** using Multi-LLM Group Relative Policy Optimization (MLGRPO) on HumanEval dataset. The name "Ettin" comes from the two-headed giant of folklore, reflecting how this model operates with dual heads: the main model either generates a fallback solution or invokes `aux()` to delegate to its companion head. ## Model Details - **Base Model**: Qwen/Qwen2.5-Coder-3B - **Training Method**: MLGRPO (Multi-LLM Group Relative Policy Optimization) - **Dataset**: HumanEval - **Task**: Code generation with auxiliary function collaboration ## Usage ```python from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("LovelyBuggies/2xQwen2.5-Coder-3B-Ettin-Aux") model = AutoModelForCausalLM.from_pretrained("LovelyBuggies/2xQwen2.5-Coder-3B-Ettin-Aux") # Generate code inputs = tokenizer(aux_prompt, return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=256) aux_completion = tokenizer.decode(outputs[0], skip_special_tokens=True).strip() cleaned_aux_completion = extract_specific_function(cleanup_code(aux_completion), "aux") print(cleaned_aux_completion) ``` ## Training Details This model was trained as part of a multi-LLM system on the full HumanEval dataset: - Agent 0 generates auxiliary functions to help solve coding problems - Agent 1 generates main functions that utilize the auxiliary functions - Both agents are trained collaboratively using MLGRPO ## Agent Role - This is the **Auxiliary Function Generator** agent that creates helper functions to assist in solving coding problems. - It provides all solutions and would be called twice in the main function generator [2xQwen2.5-Coder-3B-Ettin-Main](https://huggingface.co/LovelyBuggies/2xQwen2.5-Coder-3B-Ettin-Main) to provide a verbose solution. ## Citation If you use this model, please cite: ```bibtex Coming soon. ```