Gewu-Base-W8A16

Qwen/Qwen3.5-9B quantised to 8-bit weights: the one weight file that both serving tiers of Gewu share in the paper Gewu: Building, Enhancing, and Evaluating a Tool-Augmented 9B Physics Tutoring System (2026). The default tier hot-mounts the LoRA adapter Alumin-Hydro/Gewu-SFT (use its vllm/ folder, which carries the text-only key layout) on top of this file; the enhancement tier runs this file alone, eight samples and a vote. Text-only checkpoint (Qwen3_5ForCausalLM, 32 layers); the vision encoder of the original release is not included.

Quantisation recipe

llm-compressor GPTQ, scheme W8A16 (int8 weights, 16-bit activations), group size 128, symmetric, static activation order, dampening 0.01, targets every Linear except lm_head; 49 linear-attention sub-modules are kept in bfloat16 (listed under ignore in config.json). Calibration data: 384 problems drawn from GewuBank-20K (seed 0, rendered with the chat template, up to 2,048 tokens), i.e. the model's own working distribution rather than a generic text corpus. Saved in the compressed-tensors pack-quantized format; vLLM 0.27.1 loads it directly. The exact recipe file is included as recipe.yaml.

Measured in the paper

• Pre-registered quantisation gate (lose at most 3 pp on the paper's hard set, paired p > 0.05, no drift in tool-call or termination rate): passed. Base model, adapter off: +1.9 pp against the 16-bit weights; with the adapter: +2.5 pp; both inside the noise floor (paper Section 5.7).
• Deployment on one RTX 3090 (24 GB) under vLLM 0.27.1: 11 GB of weights plus the adapter; the KV pool holds about 230k tokens at 8k context, reported by the runtime as 28 concurrent sessions, and 265k tokens at 32k context, 8 sessions; a single stream decodes at about 58 tokens per second (paper Sections 4.6 and 5.7).
• Every accuracy in the paper was measured on merged weights; the hot-mounted form was measured equivalent to merged weights on the default tier.

Serving

vllm serve <local copy of this repo> --served-model-name gewu-base --dtype bfloat16 \
  --enable-lora --lora-modules gewu=<local copy of Alumin-Hydro/Gewu-SFT/vllm> --max-lora-rank 32 \
  --reasoning-parser qwen3 --enable-auto-tool-choice --tool-call-parser qwen3_xml

Request model=gewu for the default tier (adapter on) and model=gewu-base for the enhancement tier's samples. The SymPy sandbox and the vote are outside the model; the paper describes both.

License and citation

The weights are a quantised redistribution of Qwen3.5-9B (Apache-2.0); the calibration problems are from GewuBank-20K (CC BY 4.0). Released under Apache-2.0. Please cite the paper:

Feng, Z. (2026). Gewu: Building, Enhancing, and Evaluating a Tool-Augmented 9B Physics Tutoring System.
Research report, Yau High School Science Award (Computer Science), 2026.

Checksums: SHA256SUMS.txt. Companion repositories: Alumin-Hydro/Gewu-SFT (adapter), Alumin-Hydro/Gewu-SFT-W8A16 (the fine-tuned model merged and quantised, for serving without LoRA support), Alumin-Hydro/GewuBank-20K, Alumin-Hydro/gewu-sft-traces.