GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
CodesBee
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
CodesBee
Model Tree
Qwen/Qwen3-4B-Instruct-2507
Input Modalities
Output Modalities
Supported Functionality
Use the included decomposition.txt as the system message and the original question as the user message, with the base tokenizer's native chat template. Preserve the prompt text, including its final newline.
The output is a JSON array of supporting-question strings. Each question preserves its identifying description so it can be retrieved independently. The output contains no answers or references such as #1. An empty array is allowed. DeQA-RAG separately retrieves and answers the original question after the supporting questions.
Use greedy generation: do_sample=False, num_beams=1, max_new_tokens=1024, seed 1729, and SDPA attention. The DeQA-RAG loader explicitly sets its generation configuration to avoid inheriting sampling defaults.
After installing the DeQA-RAG project with its model dependencies:
python
from deqa.decompose import Decomposer decompose = Decomposer("CodesBee/DeQARAG")questions = decompose("Who owns the company where the composer of Song S works?")print(questions)The underlying PEFT loading pattern is:
python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM base = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen3-4B-Instruct-2507", revision="cdbee75f17c01a7cc42f958dc650907174af0554", dtype=torch.bfloat16, attn_implementation="sdpa",).to("cuda")model = PeftModel.from_pretrained(base, "CodesBee/DeQARAG").eval()The project training examples combine BREAK-high sources, HotpotQA, 2WikiMultiHopQA, MuSiQue and explicitly authored synthetic coverage examples. The project author led the design, development and review of the supporting-question annotations.
The released weights continue an existing ordinary LoRA for 40 additional optimizer updates. This continuation combines existing decomposition examples with native coverage questions and explicitly marked synthetic examples.
This adapter was developed for the project's English multi-hop QA experiments. Generated questions can omit prerequisites or change the meaning of a relation. DeQA-RAG's evaluation package includes the original saved supporting questions for its fixed evaluation pool; use those files when reproducing that evaluation.
The adapter is released under Apache-2.0. The base model's Apache-2.0 license also applies to its original materials.