GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Udit013
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
Udit013
Model Tree
Qwen/Qwen2.5-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Research and education only. Must NOT be used for real clinical decisions, diagnosis, or treatment. Outputs are uncalibrated and may be confidently wrong.
| Model | MedMCQA (in-domain) | PubMedQA (out-of-domain) |
|---|---|---|
| Base 0-shot | 47.5 | 48.0 |
| QLoRA 5K | 50.0 | 64.5 |
In-domain is flat (within noise) — strong instruction tuning already near-saturates MedMCQA; the OOD gain is likely an answer-selection/format effect, not new knowledge. See the repo for the full methodology and honest write-up.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct", device_map="auto", load_in_4bit=True)model = PeftModel.from_pretrained(base, "Udit013/qwen2.5-7b-medmcqa-qlora-5k")tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")