GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
mikekeror
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
mikekeror
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
In a pre-registered evaluation on a frozen 236-question held-out set, this adapter did not show a detectable accuracy gain over the base model with the same retrieval pipeline (SFT vs base: -2.5 points, 95% interval [-5.9, +0.9]). The accuracy gains in this project came from the retrieval and calculation pipeline around the model, not from fine-tuning. On an earlier 62-question set, fine-tuning did remove fabricated citations (11 to 0).
Full write-up: https://mikekeror-rgb.github.io/advocate_renumeration_assistant_v1/report.pdf
The adapter is trained for use inside the full pipeline, not on its own: hybrid retrieval (dense + BM25 + reciprocal rank fusion), case-scoped retrieval when a question names a ruling, and a deterministic fee calculator whose result the model is told to state. Prompts contain numbered source chunks, and the model is trained to cite them and to say "Not covered in the provided documents" when the sources do not answer.
Used without retrieved context, it has no reliable legal knowledge of its own. Code for the pipeline: https://github.com/mikekeror-rgb/advocate_renumeration_assistant_v1
With transformers and peft:
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = "Qwen/Qwen2.5-7B-Instruct"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto", torch_dtype="auto")model = PeftModel.from_pretrained(model, "mikekeror/qwen2.5-7b-advocate-sft-lora-ep1")With vLLM (multi-LoRA, base and adapters served side by side):
bash
vllm serve Qwen/Qwen2.5-7B-Instruct --enable-lora \ --lora-modules advocate-ep1=mikekeror/qwen2.5-7b-advocate-sft-lora-ep1Accuracy, percent, judged against reference answers (numeric answers checked deterministically):
| Model | Overall | Unseen rulings | Seen rulings |
|---|---|---|---|
| Base Qwen2.5-7B-Instruct | 87.7 | 78.3 | 79.2 |
| This adapter (SFT, epoch 1) | 85.2 | 75.4 | 72.9 |
Judge faithfulness (1 to 5): base 4.59, this adapter 4.59. Differences between base and SFT are within the noise of this test. A rerun of the base model changed 2 of 236 answers. The judge (gpt-5.4-mini) was hand-checked on 30 verdicts, with 30 of 30 agreeing.
Keror, M. (2026). Advocate Remuneration Assistant: pipeline engineering vs fine-tuning (software and evaluation). https://doi.org/10.5281/zenodo.23603007
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base = "Qwen/Qwen2.5-7B-Instruct"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, device_map="auto", torch_dtype="auto")model = PeftModel.from_pretrained(model, "mikekeror/qwen2.5-7b-advocate-sft-lora-ep1")vllm serve Qwen/Qwen2.5-7B-Instruct --enable-lora \ --lora-modules advocate-ep1=mikekeror/qwen2.5-7b-advocate-sft-lora-ep1