GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
dilr
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
dilr
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Model | JSON Validity | Notes |
|---|---|---|
| Qwen2.5-3B zero-shot | 0% | Invents own schema, ignores instructions |
| Mira-Q1 (this model) | 98% | Follows extraction schema correctly |
The base model produces 0/800 valid extractions — it invents field names like labTestResults, fullName instead of following the schema. Mira-Q1 fine-tuning is essential.
| Parameter | Value |
|---|---|
| Base model | Qwen/Qwen2.5-3B-Instruct |
| Method | QLoRA (4-bit, r=16, alpha=32) |
| Training data | 3,438 examples (126 curated + 3,312 Synthea-rendered) |
| Epochs | 2 |
| Final loss | 0.14 |
| GPU | Kaggle T4 (free tier) |
| Training time | ~2h 40m |
Extracts 10 required fields from clinical documents:
document_type: lab_report | medication_list | discharge_summary | pathology_report | intake_form | progress_note | otherpatient: {age, sex} — de-identified, no names/MRNencounter: {date, department}vitals[], labs[], medications[], diagnoses[], procedures[], allergies[]extraction_notespython
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModelimport torch bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_compute_dtype=torch.float16)base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct", quantization_config=bnb, device_map="auto")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct")model = PeftModel.from_pretrained(base, "dilr/Mira-Q1") messages = [ {"role": "system", "content": "You are a clinical information extraction system..."}, {"role": "user", "content": "Patient: 45/M\nHb 12.5 g/dL (13-17) LOW"},]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to("cuda")outputs = model.generate(**inputs, max_new_tokens=2048, do_sample=False)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))The base model without fine-tuning produces invalid output like:
json
{"patient": {"id": "87/F", "fullName": null, "dateOfBirth": "2024-01-29"}, "labTestResults": [{"testName": "Total Cholesterol", ...}]}Wrong field names, wrong structure, includes identifiers. Mira-Q1 fixes all of this.
Apache-2.0
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfigfrom peft import PeftModelimport torch bnb = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_compute_dtype=torch.float16)base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct", quantization_config=bnb, device_map="auto")tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-3B-Instruct")model = PeftModel.from_pretrained(base, "dilr/Mira-Q1") messages = [ {"role": "system", "content": "You are a clinical information extraction system..."}, {"role": "user", "content": "Patient: 45/M\nHb 12.5 g/dL (13-17) LOW"},]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to("cuda")outputs = model.generate(**inputs, max_new_tokens=2048, do_sample=False)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)){"patient": {"id": "87/F", "fullName": null, "dateOfBirth": "2024-01-29"}, "labTestResults": [{"testName": "Total Cholesterol", ...}]}